Global Average Pooling

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 167% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 42

Oct 1, 2026cs.LG

Pooling Helps, Learned Weighting Hurts In-Context: Decomposing Group Attention

Group attention, introduced by the time series forecasting model Chronos-2, attends over the variates of a group at a fixed patch index and serves both multivariate (MV) and in-context learning (ICL) forecasting. Rather than evaluating this cross-variate attention design as a whole, we ask which part of the mechanism earns the benefit and probe its applicability to both MV and ICL regimes. By editing the attention matrix

α

at inference we separate the two pathways a head comprises: V/O, which projects a weighted summary of the group, and Q/K, which decides the weights. Uniform pooling (V/O without any Q/K weighting) is positive on 18 of our 20 sensor-network configurations, while the learned weighting (Q/K) splits by group type: its contribution is positive or negligible for MV, but materially degrades 8 of the 10 sensor-network ICL configurations, leaving 4 of them worse than univariate inference. By isolating the impact of different layers, we find that uniforming

α

in the first block alone improves every ICL configuration we test.

Michael Fore, James Mason Inder, Mrishika Nair +2

Amazon

Global Average Pooling In-Context Learning Cross-Attention Time Series Forecasting

Sep 27, 2026cs.LG

T-SNN: Temporal Simplicial Neural Network for EEG Decoding

Decoding brain states requires models that capture both the evolution of neural activity and interactions among groups of brain regions. Existing EEG methods often treat recordings as multivariate time series or represent functional connectivity with pairwise graphs, leaving dynamic higher-order interactions largely unmodeled. We introduce the Temporal Simplicial Neural Network (T-SNN), which represents EEG recordings as sequences of evolving simplicial complexes. By combining simplicial convolutions with recurrent updates, T-SNN jointly learns higher-order interactions and their temporal evolution. On the seven-class SEED-VII emotion recognition task, T-SNN outperforms convolutional, recurrent, graph-based, and Transformer methods in both trial-wise and cross-subject evaluations. Incorporating eye-movement features further improves performance, demonstrating the framework's potential for multimodal brain-state decoding.

Nikita Malik, Shubhajit Roy, Mohit Kataria +4

Bharti School of Telecommunication Technology and Management Indian Institute of Technology, Delhi · Department of Computer Science & Engineering Indian Institute of Technology, Gandhinagar · Yardi School of Artificial Intelligence Indian Institute of Technology, Delhi +4

Electroencephalography Decoding Electroencephalography Functional Connectivity Neural Network Emotion Recognition Global Average Pooling

Sep 17, 2026eess.IV

Compression Hurts, Pooling Helps: Information Loss in Rayleigh-Scale Estimation from B-Mode Ultrasound

Clinical B-mode images are widely available as potential data sources for quantitative ultrasound (QUS) analysis for tissue characterization. However, standard clinical ultrasound devices apply unknown log-compression to RF envelope data before display and storage. Previous work has demonstrated estimation of the underlying RF envelope statistics in the presence of an unknown compression law. Using Fisher information analysis, we show that finite-offset log compression causes severe information loss when estimating the Rayleigh scale

σ

, which controls diffuse speckle. For a single image window, unknown compression raises the minimum achievable variance for unbiased estimation of

σ

by a compression-independent factor of approximately

\FisherMinInflation

. When

M

equal-sized windows share the same unknown compression settings, the excess variance decays as

1/M

; even in the most favorable regime, reducing the variance inflation factor below

1.1

requires

\FisherBestCaseWindows

windows. Our analysis treats the contrast parameter

a

as unknown and the boundary offset

b

as known; estimating

b

experimentally shows even larger variance. We validate this theory using synthetic estimation experiments and demonstrate RF-scale recovery on real RF-envelope windows from the OASBUD dataset. Together, these results clarify the limitations of using routine B-mode images for QUS.

D. Hudson Smith, Ahmer Raza

Clemson University

Ultrasound Density Ratio Estimation Fisher Information Data Compression Methods Scaling Laws Global Average Pooling

Sep 15, 2026eess.SY

Unified Heterogeneous Graph Neural Network solver for Power Flow, Optimal Power Flow and State Estimation

Power Flow (PF), Optimal Power Flow (OPF), and State Estimation (SE) are fundamental problems in power system analysis, but solving them is computationally expensive. Graph Neural Networks (GNNs) have been proposed as fast surrogates, yet existing solvers are trained for a single problem at a time, producing narrow models that must be rebuilt for each new task. We propose a more general approach: a single Heterogeneous Residual Gated Graph Convolutional Network that solves all three problems with one shared backbone. Rather than learning one mapping, the model learns a reusable representation of how the network behaves, from which PF, OPF, and SE can each be estimated. Trained jointly on the three problems across diverse topologies and loading conditions, and evaluated on the IEEE 14-bus and 118-bus systems, the shared model matches the accuracy of task-specific GNN solvers and stays robust on unseen loading levels and topologies. These results show that a single model can capture the basic operation of a power network and serve several analysis tasks at once, a first step toward a foundation model for power systems.

Ferran Bohigas-Daranas, Hamid Latif-Martínez, Eduardo Prieto-Araujo +2

Optimal Power Flow Power Systems Graph Neural Networks Neural Solvers State Estimation Global Average Pooling

Sep 14, 2026cs.AI

Competence-Gated Pooling of Language Models and Priors for Event Forecasting

In hybrid forecasting, a language model is often one of several available signals. A system may already have a market, crowd, or statistical forecast and must decide whether the model adds useful information or should be ignored. The relevant target is therefore not standalone model accuracy, but relative competence, defined as the model's marginal value beyond the available external forecast. Under Brier loss, we characterize when model disagreement can improve an external forecast and derive the gain from using domain-specific rather than global pooling weights. We then introduce a competence gate that estimates domain-level source weights from resolved outcomes, shrinks uncertain estimates toward a global weight, and recalibrates the pooled forecast. Across 2,357 resolved binary questions and five language models, the gate improves the main external baseline from 0.0771 to 0.0732 Brier and significantly outperforms global forecast combinations. The gain remains significant under leakage controls and against a leakage-safe time-series prior on the pooled structured set, with separate evidence on FRED. In contrast, the gate gives no significant improvement on the official ForecastBench market subset, where it largely defers to the market. Across four Qwen models, verbal confidence does not reliably identify when the model outperforms the external forecast, while outcome-estimated competence supports better abstention decisions. These results provide a practical approach for selective model use based on measured marginal value.

Aditi Tiwari, Aashrith Bandaru, Heng Ji

University of Illinois Urbana-Champaign Urbana, Illinois, USA

Large Language Model Forecasting Competence Global Average Pooling

Sep 8, 2026cs.RO

Localized Visual Feature Aggregation via Focus Pooling for Visuomotor Policies

Focusing on spatially localized, control-relevant visual cues has been shown to improve data efficiency in visuomotor policies by reducing the need to model task-irrelevant visual variation. Existing methods often impose this focus through input preprocessing, such as cropping control- or object-centric regions in RGB images or point-clouds. However, it remains underexplored whether such localized features can be exposed directly from commonly used convolutional neural network (CNN) encoded features. In this paper, we show that intermediate CNN features preserve localized visual context for control, but existing pooling methods fail to aggregate it effectively. We introduce FocusPool, an attention pooling module that selectively aggregates intermediate visual features according to their relevance to the robot's current proprioceptive context. The resulting pooled representation captures task-progressive, control-relevant local information and is used directly for policy learning. Across simulation and real-world experiments, FocusPool improves policy success rates over pooling and explicit local focus methods by 36.2% and 41.2%, with training only 5.8% of encoder parameters.

Ruiyu Wang, Zheyu Zhuang, Danica Kragic +1

KTH Royal Institute of Technology, Sweden

Visuomotor Policy Global Average Pooling Spatial Attention Feature Pyramid Sequential Visual Localization Visual Cues

Sep 7, 2026cs.IR

Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval

Late-interaction visual document retrievers preserve fine-grained page evidence by storing many token embeddings per page, but the resulting storage and query-time interaction costs make large-scale deployment expensive. Pooling document tokens before indexing offers a natural remedy, yet static pooling must decide which visual evidence to preserve before the query is known. We study an alternative: a heavily compressed hot-path index generates candidates, after which query-aware token budgeting operates on the original token sets of the shortlisted pages. We formulate this stage-two selection as a budgeted MaxSim coverage problem, show that a clipped version is monotone submodular, and compare coverage-only, cluster-guided, token-wise, and marginal-gain policies. On ten ViDoRe tasks with ColModernVBERT, direct static pooling reduces macro normalized discounted cumulative gain at rank five from 0.6309 without compression to 0.4738 at a thirty-two-fold pool factor. Under the same candidate-generation regime and a pool-factor-eight-equivalent reranking budget, token top-k recovers 93.93 percent of the full-token score, while greedy marginal-gain selection recovers 98.39 percent. Held-out and leave-one-dataset-out evaluations yield positive greedy improvements over token top-k on every dataset. The latency analysis reveals two useful operating points: token top-k for interactive retrieval and the naive greedy implementation as a quality upper envelope. Together, these results show that late-interaction visual retrieval benefits from query-aware allocation rather than query-agnostic pooling alone.

PS Rishi, Rajeev Ranjan Dwivedi, Vinod K Kurmi

Indian Institute of Science Education and Research Bhopal (IISER Bhopal), India

Visual Document Retrieval Global Average Pooling

Sep 1, 2026stat.ML

Pooling and Drift in Delayed Bandits

A system often has to act long before it learns whether the act worked: a recommender sees a click in seconds and a purchase in days. With

K

actions and a delay of

d

rounds, the best rate known for this setting is

\widetilde{O}(\sqrt{(K+d)T})

over

T

rounds, so a longer menu is always more expensive to learn from. It need not be: if the outcome depends on the action only through the state it produced, then one late outcome informs every action that could have produced the observed state, and the price is set by how many genuinely different states the actions produce rather than by how many actions there are. We measure this using an effective dimension

v_t

between

1

and the number of states, and prove

\widetilde{O}(\sqrt{(d+1)V\log K})

for a rotating algorithm and

\widetilde{O}(\sqrt{V^{-}}+\sqrt{dT})

for the single-copy algorithm used in practice, for any budget fixed in advance; merging similar states lowers the price further, at an explicit bias. Even when given the exact losses from

d

rounds ago, no algorithm escapes

Ω(\sqrt{dE\min\{1+\log J,T/d\}})

, where

J

counts the drifting directions and

E

bounds how far losses move while the learner waits. On generated data, the state channel cuts regret by up to 79 percent against action-level weighting and, on the funnel family, by 32 to 68 percent against a tuned minimax-optimal method.

Melika Baghi

Georgia Institute of Technology

Stochastic Multi-Armed Bandits Minimax Optimal Sample Complexity Position Bias Global Average Pooling

Sep 1, 2026cs.AI

FLaG: Frequency-Domain Latent-attention Gated Pooling for Token Aggregation

Token aggregation converts token-level representations into fixed-dimensional sample representations, but most pooling methods operate only in the original token space. We introduce Frequency-Domain Latent-attention Gated Pooling (FLaG), a plug-in aggregation module that re-expresses encoder outputs in the Fourier domain before final pooling. FLaG represents the nonredundant rFFT spectrum through concatenated real and imaginary components, summarizes spectral tokens with learnable latent queries, derives a sample-conditioned channel gate, and reconstructs modulated token representations for downstream aggregation. We evaluate the same architecture across ESM2-based antimicrobial peptide (AMP) activity prediction, ResNet18 image classification on CIFAR-10 and CIFAR-100, and three RoBERTa-based language tasks. FLaG achieves the best macro-averaged Spearman correlation coefficient, RMSE, and Recall@50 across four AMP backbone-species settings and the highest top-1 accuracy on CIFAR 10. It also achieves the best mean results on five of seven language metrics, although mean pooling remains strongest on STSBenchmark. AMP-side mechanistic analyses reveal low-frequency prediction sensitivity across most encoder layers, with increased relative high-frequency sensitivity in the final layer, and pronounced peptide-specific positional responses. The residual gate broadly amplifies spectral channels while preserving the low-frequency-dominated energy profile, whereas latent cross-attention exhibits sample- and species-specific spectral allocation. Overall, FLaG provides a transferable frequency-domain aggregation bias across protein, visual, and textual representations, with benefits that depend on the backbone and downstream task. Supplementary materials, source code, and data are available at https://www.healthinformaticslab.org/supp/ and https://github.com/Kewei2023/AMPCliff/tree/FLaG.

Kewei Li, Rongying Zhang, Xueli Wang +6

College of Computer Science and Technology, Jilin University, Changchun, 130012, China. · Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China. · Institute for Quantitative and Computational Biology, University of California, Los Angeles, 90024, United States of America. +4

Global Average Pooling Fourier Token-Level Uncertainty

Aug 30, 2026cs.AI

Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval

Multi-modal late-interaction retrievers achieve strong retrieval on visually rich documents by representing each page as per patch embeddings and matching at the token level. However, this approach incurs high storage costs. Existing compression methods typically fix a single compression level at indexing time, limiting flexibility. We present ColSNAP (Spatial Nested Average Pooling)1, a training method that generates a nested hierarchy of compression levels directly from a backbone's patch grid. By spatially pooling patch embeddings into pro- gressively coarser tiers and training all tiers simultaneously, a single model learns to support retrieval at multiple compression levels without architectural changes. Crucially, a single encoding pass yields every tier, enabling the accuracy-storage trade-off to be configured at indexing time to match avail- able storage budgets, rather than being fixed during training. We demonstrate that models trained using ColSNAP maintain near full-resolution retrieval performance under substantial compression and that ColSNAP transfers effectively across multiple late-interaction backbones, and achieves most of its improvements via a lightweight adaptation stage applied to a pre-trained retriever.

Trishan Singha Roy, Arkadeep Acharya, Vishwajeet Kumar +2

IIT Delhi · IBM

Multimodal Retrieval Visual Document Retrieval Visual Embeddings Matryoshka Representation Learning Global Average Pooling

Aug 5, 2026cs.CV

EndoVLM: An Endoscopy Vision-Language Pre-training Model via Anatomy-Guided Sparsity and Progressive Alignment

The development of foundation models (FMs) is crucial for advancing endoscopic image analysis. However, existing endoscopy FMs mainly rely on self-supervised learning from uni-modal images or videos, overlooking the rich semantic knowledge contained in clinical reports. Furthermore, effectively leveraging these records is hindered by a fundamental modality gap: structured anatomical descriptions are not naturally mapped to specific frames within the high-redundancy, uncurated visual streams. In this paper, we present EndoVLM, a novel vision-language FM pre-trained on over 348K endoscopic examinations, each pairing a clinical report with its corresponding image collection. An Anatomy-Guided Sparse Pooling mechanism utilizes textual descriptions as queries to drive sparse attention, efficiently aggregating semantically salient frames into anatomy-specific visual representations across redundant image-sets. Next, a Progressive Semantic-Aware Alignment strategy models clinical taxonomy (anatomy and pathological status) via structured soft targets, bridging the gap from global patient-level matching to fine-grained localized alignment. Finally, a Semantic-Concentrated Masked Autoencoder is applied exclusively to these semantic-rich frames, integrating low-level visual precision with robust high-level semantic representation. Extensive experiments across various downstream tasks demonstrate that EndoVLM outperforms existing foundation models and remains competitive with task-specific methods. Remarkably, EndoVLM also exhibits robust zero-shot generalization capabilities, highlighting its potential for broader clinical application.

Zhenyu Yi, Jianwei Xu, Yue Hu +6

1DAMO Academy, Alibaba Group · 3Shanghai Jiao Tong University · 4Hupan Lab +3

Vision-Language Alignment Colonoscopy Recent Vision Foundation Models Modality Gap Global Average Pooling

Aug 4, 2026cs.LG

Learning and Clustering on Temporal Graphs: Principles, Primitives, and Pooling

This work focuses on the problem of learning on temporal graphs, with particular emphasis on the task of clustering: obtaining coarse-grained representations by aggregating information from nodes, edges, and temporal dynamics - a task related to pooling in machine learning on graphs, or community detection in network science. Although graph neural networks reach state-of-the-art performance across many downstream graph tasks, their advantage over established descriptive and inferential clustering algorithms is far less settled, especially under demands of efficiency and recovery accuracy. We frame this tension through three linked perspectives: principles, connecting graph learning and community detection through shared spectral foundations and detectability thresholds in stochastic block model regimes; primitives, making spectral clustering and multislice modularity optimization tractable through GPU-accelerated temporal backends; and pooling, viewing principled community detection as a theory-grounded coarse-graining operator for temporal graphs. Our results indicate that algorithmic methods remain the appropriate tool where attributes are absent or weak - scalability rather than accuracy being the binding obstacle - while neural models are most compelling when structural, temporal, and attribute signals align. By making temporal clustering scalable, GPU-accelerated primitives suggest a route toward theory-grounded pooling, while raising a central question: when does community-based coarse-graining preserve the dynamics needed for downstream learning tasks?

Nelson Aloysio Reis de Almeida Passos, Emanuele Carlini, Salvatore Trani

University of Pisa, Dept. of Computer Science, 56127 Pisa PI, Italy · National Research Council, 56124 Pisa PI, Italy

Temporal Graph Neural Networks Community Detection Graph Neural Networks Clustering Global Average Pooling Coarse

Jul 8, 2026cs.CL

Riemannian Geometry for Pre-trained Language Model Embeddings

Understanding the geometric structure of pre-trained language model embeddings matters for interpretability and safety. We ask whether sentence-level classification signal lives in the Riemannian geometry of contextual token embeddings, and probe it by extracting per-token pullback metrics from a learned encoder's analytical Jacobian and aggregating them with the Fréchet mean on the symmetric positive definite (SPD) manifold; we call this procedure Riemannian Mean Pooling (RMP). Across three datasets with non-trivial linguistic structure (CoLA, CREAK, RTE), RMP outperforms Euclidean mean pooling, while on FEVER-Symmetric, a benchmark constructed to remove annotation-driven lexical artifacts, the method correctly stays at chance. Ablations show that a randomly initialised encoder combined with Fréchet aggregation already beats Euclidean pooling on two of the three signal-bearing datasets, localising the source of the gain to the geometric aggregation rather than to learned manifold structure; the trained encoder contributes additional signal specifically on CREAK, the most knowledge-heavy of the three signal-bearing datasets.

Szczepan Konior, Alexandre Quemy, Przemysław Klocek +2

IBM Automation and AI, Krakow, Poland · Hother, Krakow, Poland · University of Warsaw +1

Token Embeddings Text Embeddings Riemannian Manifolds Global Average Pooling

Jul 3, 2026eess.AS

Mixture-Constrained Max Pooling Improves Separation-Based Bird Species Classification

Bird species classification from field recordings remains challenging due to overlapping vocalizations and incomplete species labels. We study source separation as a preprocessing for bird species classification to improve multi-species detection. Specifically, we employ an ensemble of two separators, FTRNN and TF-Locoformer, both trained with mixture invariant training (MixIT). To address the false positive gain caused by separation errors in separated outputs, we propose mixture-constrained max pooling (MCM), which clips the predicted probability from each separated channel based on the corresponding species probability in the original mixture. The classifier is applied to each separated output and the original mixture independently, and MCM aggregates the predictions into a final per-species probability. Experiments on two real-world datasets show that the ensemble outperforms individual separators and MCM outperforms standard max pooling across multiple metrics, and reveal that separation leads to both true positive gain for present species and false positive gain for absent species.

Yuzhu Wang, Kalle Lahtinen, Patrik Lauha +4

Signal Processing Research Center, Tampere University, Tampere, Finland · Faculty of Biological and Environmental Sciences, University of Helsinki, Helsinki, Finland · Department of Biological and Environmental Science, University of Jyväskylä, Jyväskylä, Finland

Species Identification Animal Vocalizations Speech Separation Separation Mixture Models Global Average Pooling

Jun 22, 2026cs.IR

Unlocking Spatial Grounding in Large Audio-Visual Retrieval models

Weak supervision sets a practical regime for audio-visual sound source localization as dense spatial annotations are costly to obtain at scale. The task, however, remains challenging, as models must locate sound sources from temporally aligned audio-visual data without pixel-level supervision. Recent large-scale audio-visual retrieval models, trained at unprecedented scale, encode rich multimodal structure. We show their latent representations, though optimized for global alignment, can nonetheless enable fine-grained spatial grounding. While spatial detail is progressively lost in the upper layers of retrieval backbones due to global pooling, intermediate visual tokens retain highly structured spatial information. To exploit this, we introduce LAIP (\emph{Localization via Audio-Informed Pooling}), a framework that employs a lightweight \emph{Audio-informed Spatial Pooling} (AiSP) to replace the standard global aggregation module. By querying intermediate visual tokens with audio aligned at the frame level, LAIP recovers localized spatial information that is otherwise discarded by the retrieval pipeline, with the largest gains observed for PE-AV, a stack with underlying temporal aggregation. Our approach achieves state-of-the-art performance on AVSBench and AVATAR, nearly doubling previous results on the latter, improving average CIoU from 13.21 to 26.22.

Hugo Malard, Michel Olvera, Sanjeel Parekh +3

LTCI, Télécom Paris, Institut Polytechnique de Paris, France · Meta, Reality Labs Research · NVIDIA, France +1

Audio-Visual Reasoning Sound Source Localization Spatial Grounding Dense Annotation Global Average Pooling

Jun 19, 2026cs.LG

Decodable but Not Faithful: Coupling Natural-Language Rationales to Programmatic Verifiers

Language models can generate plausible rationales for their predictions, but these explanations may not faithfully represent the model's internal reasoning. We propose verifier-coupled reasoning, a framework that inserts inline claims into reasoning traces and trains an auxiliary consistency head to predict programmatic verifier outputs from rationale-span hidden states. The central finding is a gap between decodability and faithfulness: consistency training reliably makes verifier information decodable from rationale representations, but decodability does not guarantee faithful generation. In LeanCheck (formal theorem proving), rationale-only and proof-only pooling achieve perfect directional separation under counterfactual conflict. In KataGo (Go engine), commentary spans encode 10-way win-rate buckets at 81% accuracy. Yet in a code setting, the model achieves 98.6% coupling while its generated explanations remain unfaithful: fluent prose with correct structured claims, but describing unrelated algorithms; a controlled pretrained-vs-from-scratch comparison shows the gap is not capacity-driven. Synthetic activation patching confirms causal influence (73-89% vs. 31% baseline), FEVER reveals that evidence-only pooling isolates genuine evidence sensitivity at the cost of raw accuracy, and per-claim analysis shows that consistency loss disproportionately benefits fine-grained claims over binary ones. These results establish that consistency losses are effective diagnostics and representation-shaping tools, but not sufficient conditions for faithful reasoning.

Vatsal Ananthula, Adarsh Kumarappan

University of California, Berkeley · 2California Institute of Technology

Free-Form Textual Rationales Decoding Global Average Pooling

Jun 18, 2026cs.LG

Hierarchical Pooling for Sheaf Neural Networks

Sheaf Neural Networks (SNNs) generalize Graph Neural Networks (GNNs) by replacing scalar node signals with stalk-valued signals and by using restriction maps to measure compatibility across edges. Unlike standard graph diffusion, which encourages neighboring node features to become similar, sheaf diffusion promotes consistency through the restriction maps and can therefore model more general relationships between neighboring nodes. However, existing sheaf neural architectures mainly operate at a fixed graph resolution and do not provide a principled pooling mechanism for building hierarchical representations. In this paper, we introduce Hierarchical Sheaf Pool (HiSP), a sheaf-aware pooling framework based on local spectral coarsening. Given a partition of the graph, HiSP constructs each coarse stalk by projecting fine stalk-valued features onto the low-frequency eigenmodes of the cluster-internal sheaf Laplacian. These local modes define a cochain-level prolongation map, which allows the fine sheaf energy to be represented on the coarse space through a Galerkin operator. We further analyze the approximation induced by coarsening by separating truncation loss, due to discarded local modes, from realization loss, due to representing the projected operator as a coarse sheaf. Finally, we implement HiSP as a GNN pooling layer compatible with SNNs and provide a PyG implementation supporting batching, lifted sheaf Laplacians, and hierarchical architectures.

Dionisia Naddeo, Carlo Abate, Pietro Liò +2

UiT The Arctic University of Norway · UiT The Arctic University of Norway NORCE Norwegian Research Centre AS

Sheaf Neural Networks Sheaf Graph Neural Networks Global Average Pooling Graph Laplacians

Jun 16, 2026cs.LG

Credibility-Weighted Pricing of Autonomous Vehicle Liability Under Operational Design Domain Shift

Automated Driving System deployments create a foundational ratemaking challenge: sparse experience, shifting operational design domains, and non-stationary risk across software releases. We propose a hierarchical Bayesian credibility framework pooling across cities, software versions, and territories via a learned ODD-similarity kernel, nesting Buhlmann-Straub as a limiting case. Demonstrated on 648 verified-engaged Waymo crashes across four U.S. metros from the NHTSA Standing General Order database against 116 million matched miles, city-aggregate credibility weights are moderate (0.12-0.46), partial pooling decisively outperforms no pooling, and a power analysis shows the learned kernel's advantage becomes detectable at approximately twelve deployed cities.

Doyeon Jang

Doyeon Jang

Automated Vehicles Credit Assignment Waymo Open Motion Dataset Actuarial Ratemaking Cities Global Average Pooling

Jun 12, 2026cs.CV

FlexPooling with Simple Auxiliary Classifiers in Deep Networks

In computer vision, the basic pipeline of most convolutional neural networks consists of multiple feature extraction layers, where the input signal is downsampled to a lower resolution in each subsequent layer. This downsampling process is commonly referred to as pooling, which is an essential operation in CNNs. Pooling improves robustness against transformations, reduces the number of trainable parameters, increases the receptive field, and lowers computation time. Since pooling is a lossy process but remains important for extracting high-level information from low-level representations, it is important to preserve the most prominent information from previous activations to improve network discriminability. Standard pooling is usually performed using dense pooling methods, such as max pooling or average pooling, or through strided convolutional kernels. In this paper, we propose a simple yet effective adaptive pooling method, called FlexPooling, which generalizes average pooling by learning a weighted average over activations jointly with the rest of the network. We further show that attaching Simple Auxiliary Classifiers (SAC) to the CNN improves performance and demonstrates the effectiveness of the proposed method compared with standard pooling methods. Experiments on multiple popular image classification datasets show that FlexPooling consistently outperforms baseline networks, achieving approximately 1 to 3 percent improvement in accuracy.

Muhammad Ali, Omar Alsuwaidi, Salman Khan

Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence · Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE

Global Average Pooling Convolutional Neural Networks Deep Network Subsampling Object-Level Control

Jun 12, 2026cs.CV

Rethinking Global Average Pooling: Your Classifier Is Secretly a Multi-Instance Learner

Modern image classifiers widely adopt global average pooling (GAP) followed by a linear classification head. This linearity ensures that the image-level logits equal the average of logits obtained by applying the classification head pointwise to the feature grid prior to GAP. Consequently, standard classifiers may inherently retain spatial class evidence that remains recoverable even when the image-level prediction is incorrect. This structure naturally suggests a multiple-instance learning (MIL) interpretation, where an image is viewed as a bag of spatial instances. Within this formulation, we demonstrate that standard classifiers trained with a single label per image can still learn the intended classification task in multi-object scenes. We further exploit this property to decompose image-level logits into a prediction grid, providing a post-hoc diagnostic to extract spatial class evidence that GAP otherwise obscures. Our systematic evaluation reveals that off-the-shelf models consistently recover the ground-truth class within foreground regions. The MIL interpretation further suggests that common classifier failures reflect known limitations of mean aggregation.

Aray Karjauv

indigo bunting

Multiple Instance Learning Image Classification Global Average Pooling Multimodal Classification Feature Pyramid Fine-Grained Perception+2

Jun 10, 2026cs.SD

SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing

We present SpAArSIST, a deployment-oriented refinement of the widely used AASIST graph pooling backend for self-supervised learning (SSL) based anti-spoofing. Motivated by redundant operations in public implementations, we replace learned pooling and stack-node attention with explicit, lightweight choices: separate train and inference graph pooling ratios

(k_{\mathrm{tr}},k_{\mathrm{inf}})

, magnitude-based node scoring, and mean aggregation of graph nodes. The best overall configuration (rank 1) cuts backend compute by 20.7% (195.045M

\rightarrow

154.706M MACs) and model size by 4.1% (611.8k

\rightarrow

586.4k params), while improving out-of-domain robustness on In-the-Wild to 2.82% EER and 0.078 minDCF (from 4.64% and 0.133) and remaining competitive on ASVspoof5. We further provide a composite selection score that summarizes accuracy, calibration, and compute to support balanced deployment-oriented model choice.

Anton Firc, Vojtěch Staněk, Zbyněk Lička +2

Spoofing Self-Supervised Learning Fast Inference Global Average Pooling Assistant

Jun 8, 2026cs.LG

Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets

Convolutions have successfully transitioned from image processing to the complex realm of non-Euclidean higher-order domains, particularly in hypergraphs. Despite the success in convolution, the exploration of a popular architecture named U-Net remains largely unexplored for hypergraph data due to the lack of well-defined pooling and unpooling operations. This work pioneers the study of U-Net architectures for hypergraph data, addressing the critical challenge of designing effective pooling and unpooling operations that retain maximal structural information from the input hypergraph. Motivated by hierarchical clustering, we propose to construct the pooling and unpooling operators all at once by cutting the clustering dendrogram at different granularities, named the Parallel Hierarchical Pooling (PHPool) and Unpooling (PHUnpool) operators. Unlike existing pooling methods that risk local structural damage through a sequential learning procedure, our PHPool operators are designed in a global and parallel manner to ensure fidelity to the original hypergraph structure with efficient computation while the PHUnpool operators are tailored to perform inverse operations of the PHPools for hypergraph reconstruction. We validate our model through hypergraph reconstruction simulation, hypergraph classification, and node-level anomaly detection, where it demonstrates superior performance over existing state-of-the-art graph and hypergraph deep learning methods.

Fuli Wang, Wei Qian, Daniel L. Lau +1

Institute for Financial Services Analytics, University of Delaware, Newark, DE, 19716, USA · Department of Applied Economics and Statistics, University of Delaware, Newark, DE, 19716, USA · Department of Electrical and Computer Engineering, University of Kentucky, Lexington, KY 40506 USA +1

Hypergraphs U-Net Convolutional Global Average Pooling Deep Learning Neural Network

Jun 3, 2026cs.CV

ORACLE-CT: Anatomy-Aware Support Pooling for CT Classification

Abdominal CT disease classification is challenging because each scan is a large 3D volume with many possible findings, while diagnostic evidence is often confined to specific organs or anatomical compartments. Most study-level classifiers aggregate encoder features using anatomy-agnostic pooling or attention, creating a mismatch between localized disease evidence and global evidence aggregation. We propose ORACLE--CT, an encoder-agnostic anatomy-aware aggregation framework that uses multi-organ segmentation to define label-specific anatomical supports and restrict attention pooling to relevant regions. The framework supports single-organ, multi-organ union, comparative, localized, and global support strategies. We evaluate ORACLE--CT with three encoder families: DINOv3, I3D--ResNet-121, and the radiology-native Pillar--0 encoder. Models are trained end-to-end on MERLIN and evaluated internally and under frozen external transfer to Duke--Abdomen and AMOS. Compared with global average pooling, support-masked pooling improved MERLIN macro-AUROC/AUPRC from 0.838/0.638 to 0.858/0.676 for DINOv3 and from 0.829/0.617 to 0.848/0.659 for I3D--ResNet-121. On harmonized 10-label external evaluation, DINOv3 improved on Duke--Abdomen from 0.802/0.628 to 0.835/0.683 and on AMOS from 0.742/0.313 to 0.762/0.350, with similar gains for I3D--ResNet-121. For Pillar--0, most gains came from learned attention, with smaller additional benefit from anatomical masking. ORACLE--CT improves discrimination and external robustness while preserving an auditable link between predictions and anatomical evidence.

Lavsen Dahal, Yubraj Bhandari, Geoffrey Rubin +1

Electrical and Computer Engineering, Pratt School of Engineering, Duke University, Durham, 27708, North Carolina, USA · Department of Mathematics, Trinity College of Arts & Sciences, Duke University, Durham, 27708, North Carolina, USA · Department of Radiology and Imaging Sciences, University of Arizona College of Medicine, Tucson, 85004 Arizona, USA +1

Semi-Supervised Medical Image Segmentation Global Average Pooling Oracles

Jun 1, 2026math.DG

Theoretical Aspects of Lie Groupoid and Lie Algebroid Equivariant Convolutional Neural Networks

We introduce Lie groupoid equivariant neural networks as a specialization of recently proposed topological category-equivariant neural networks to the differentiable setting. Lie groupoid equivariant neural networks are composed from Lie groupoid lifting convolutions and Lie groupoid convolution layers, and we show how for suitable Lie groupoids they are equivalent to certain Lie algebroid-equivariant neural networks. We additionally describe groupoid invariant global pooling as a generalization of group invariant global pooling. Furthermore, we show that each of the aforementioned layers is a special case of recently introduced admissible category-equivariant layers by demonstrating that they define continuous natural transformations between continuous feature functors.

Michael Astwood

Department of Mathematics, University of Manitoba, Winnipeg, MB, R3T 2M6 Canada

Equivariant Neural Networks Neural Network Lie Group Global Average Pooling Theory

May 25, 2026physics.chem-ph

Machine Learning Multiscale Interactions

Realistic physical systems are characterised by emergent interactions across multiple length and time scales, posing a significant challenge for predictive machine learning (ML) models. Most scientific ML models focus on a narrow range of interactions. While machine learning force fields (MLFFs) offer near-quantum accuracy, the ubiquitous message-passing layers miss long-range many-body effects. Here we introduce the Multiscale Structural Ensemble (MuSE), a hierarchical model that uses Soft Coarse-Graining Pooling to construct coarse representations from smooth fractional assignments of atoms to coarse nodes, enabling MLFF modules to operate across multiple scales. MuSE is architecture-agnostic and coupled with SO3krates, MACE, and PaiNN MLFFs for both molecules and materials. We demonstrate the power of MuSE through Hessian-based benchmarks, folding trajectories for biomolecules, and energy profiles in molecule-graphene nanostructures, where MuSE accurately captures quantum-mechanical interactions at relevant scales -- unlike other recent long-range ML models.

Àlex Solé, Sergio Suárez-Dou, Albert Mosella-Montoro +4

Image Processing Group – Signal Theory and Communications Department, Universitat Politècnica de Catalunya, Barcelona, Spain. · Inorganic and Organic Chemistry Department and Institute of Theoretical and Computational Chemistry, Universitat de Barcelona, Barcelona, Spain. · Department of Physics and Materials Science, University of Luxembourg, Luxembourg City, Luxembourg.

Molecular Dynamics Many-Body Physics Multiscale Global Average Pooling

May 25, 2026q-bio.QM

What Molecular Structure Cannot Tell Us: A Taxonomy of Explainability Gaps in GNN-Based Drug Toxicity Prediction

Not all clinically relevant adverse effects are structurally inferable from molecular graphs - regardless of model quality or architectural complexity. This study introduces an operational taxonomy of the structural information limits that prevent structure-based toxicity prediction, independent of the learning algorithm employed. Graph Neural Networks (GNNs) have emerged as a natural approach for molecular toxicity prediction, operating directly on atomic connectivity without the information loss inherent to fixed-length fingerprints. However, the fraction of a drug's known pharmacological profile that is actually inferable from molecular structure remains systematically underexplored. A systematic case study using acetylsalicylic acid (ASA, Aspirin) - one of the most comprehensively characterized drugs in pharmacology - serves as model compound. A Message Passing Neural Network (MPNN) is trained on the Tox21 benchmark and GNNExplainer is applied to characterize atom-level attribution. Results indicate that molecular structure explains approximately 45% (5/11) of known ASA adverse effects. A four-category Gap Taxonomy (GAP-1 through GAP-4) is introduced distinguishing between principally non-encodable effects, data gaps arising from Missing Not At Random (MNAR) mechanisms, assay panel mismatches, and representation errors. The MNAR gap is empirically quantified via a systematic ChEMBL query (42 documented assays, 0 retrievable bioactivity entries). An attention pooling experiment localizes the representation error to the MPNN message passing layers rather than the aggregation step. The Gap Taxonomy has direct implications for drug safety signal detection and regulatory frameworks including Good Pharmacovigilance Practice (GVP) guidelines and New Approach Methodologies (NAMs). Structural limits identified are confirmed in a companion DDI ablation study.

Juergen Dietrich

Absorption, Distribution, Metabolism, And Excretion Molecules Pharmacokinetics Toxicity Biomedical Knowledge Graph Taxonomy+1

May 21, 2026cs.AI

Enhancing Visual Token Representations for Video Large Language Models via Training-Free Spatial-Temporal Pooling and Gridding

Recent advances in Multimodal Large Language Models (MLLMs) have significantly advanced video understanding tasks, yet challenges remain in efficiently compressing visual tokens while preserving spatiotemporal interactions. Existing methods, such as LLaVA family, utilize simplistic pooling or interpolation techniques that overlook the intricate dynamics of visual tokens. To bridge this gap, we propose ST-GridPool, a novel training-free visual token enhancement method designed specifically for Video LLMs. Our approach integrates Pyramid Temporal Gridding (PTG), which captures multi-grained spatiotemporal interactions through hierarchical temporal gridding, and Norm-based Spatial Pooling (NSP), which preserves high-information visual regions by leveraging the correlation between token norms and semantic richness. Extensive experiments on various benchmarks demonstrate that ST-GridPool consistently enhances performance of Video LLMs without requiring costly retraining. Our method offers an efficient and plug-and-play solution for improving visual token representations. Our code is available in https://github.com/bingjunluo/ST-GridPool.

Bingjun Luo, Tony Wang, Hanqi Chen +1

1Tsinghua University · 2Shenzhen University · 3Xidian University

Long Visual-Token Sequences Global Average Pooling Grid

May 15, 2026cs.RO

LAPS: Improving Incremental LiDAR Mapping using Active Pooling and Sampling for Neural Distance Fields

Neural distance fields offer a compact and continuous representation of 3D geometry, making them attractive for incremental LiDAR mapping. However, their online optimization is vulnerable to catastrophic forgetting, where new observations can degrade previously reconstructed geometry. Replay-based training is commonly used to address this issue, but existing methods typically rely on passive replay buffers and uniform sampling, which can waste memory on redundant observations and under-train poorly constrained regions. We propose LAPS, a replay management framework for incremental neural mapping that improves both replay retention and replay allocation during online updates. LAPS combines reliability-based active pooling to retain reliable historical samples under limited memory with uncertainty-guided active sampling to focus optimization on under-constrained regions. Experiments on synthetic and real-world benchmarks show that LAPS consistently improves reconstruction completeness while maintaining competitive geometric accuracy. On Oxford Spires, it improves recall by 4.66 pp and F1-score by 3.79 pp over PIN-SLAM on the Blenheim Palace 05 sequence. We release our open source implementation at: https://github.com/dongjae0107/LAPS.

Dongjae Lee, Wooseong Yang, Yifu Tao +2

Department of Mechanical Engineering, Seoul National University, S. Korea · Oxford Robotics Institute at the University of Oxford, UK

Continuous Distance Field Orb-Slam2 3D Mapping Replay Global Average Pooling

May 12, 2026cs.CV

Fill the GAP: A Granular Alignment Paradigm for Visual Reasoning in Multimodal Large Language Models

Visual latent reasoning lets a multimodal large language model (MLLM) create intermediate visual evidence as continuous tokens, avoiding external tools or image generators. However, existing methods usually follow an output-as-input latent paradigm and yield unstable gains. We identify evidence for a feature-space mismatch that can contribute to this instability: dominant visual-latent models build on pre-norm MLLMs and reuse decoder hidden states as predicted latent inputs, even though these states occupy a substantially different norm regime from the input embeddings the model was trained to consume (Xie et al., 2025; Li et al., 2026; Team et al., 2026). This mismatch can make direct latent feedback unreliable. Motivated by this diagnosis, we propose GAP, a Granular Alignment Paradigm for visual latent modeling. GAP aligns visual latent reasoning at three levels: feature-level alignment maps decoder outputs into input-compatible visual latents through a lightweight PCA-aligned latent head; context-level alignment grounds latent targets with inspectable auxiliary visual supervision; and capacity-guided alignment assigns latent supervision selectively to examples where the base MLLM struggles. On Qwen2.5-VL 7B, the resulting model achieves the best mean aggregate perception and reasoning performance among our supervised variants. Inference-time intervention probing further suggests that generated latents provide task-relevant visual signal beyond merely adding token slots.

Yanting Miao, Yutao Sun, Dexin Wang +8

1Qwen Large Model Application Team, Alibaba · 3Zhejiang University · University of Waterloo +1

Latent Visual Reasoning Multimodal Large Language Models Visual Reasoning Global Average Pooling

May 12, 2026cs.CV

The Missing GAP: From Solving Square Jigsaw Puzzles to Handling Real World Archaeological Fragments

Jigsaw puzzle solving has been an increasingly popular task in the computer vision research community. Recent works have utilized cutting-edge architectures and computational approaches to reassemble groups of pieces into a coherent image, while achieving increasingly good results on well established datasets. However, most of these approaches share a common, restricting setting: operating solely on strictly square puzzle pieces. In this work, we introduce GAP, a set of novel jigsaw puzzles datasets containing synthetic, heavily eroded pieces of unrestricted shapes, generated by a learned distribution of real-world archaeological fragments. We also introduce PuzzleFlow, a novel ViT and Flow-Matching based framework for jigsaw puzzle solving, capable of handling complex puzzle pieces and demonstrating superior performance on GAP when compared to both classic and recent prominent works in this domain.

Ofir Itzhak Shahar, Gur Elkin, Ohad Ben-Shahar

Stein Faculty of Computer and Information Science Ben-Gurion University of the Negev, Israel

Puzzle Computer Vision Shapes Constraint Language Global Average Pooling

May 11, 2026cs.CV

Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation

Automated, clinician-grade assessment reports for surgical procedures could reduce documentation burden and provide objective feedback, yet remain challenging due to the difficulty of aligning dense spatio-temporal video representations with language-based reasoning and the scarcity of high-quality, privacy-preserving datasets. To address this gap, we establish a benchmark comprising 214 high-quality simulated surgical videos paired with surgeon-authored evaluation reports. Building on this resource, we propose a Perception-Alignment-Reasoning framework for surgical video report generation, featuring Hi-GaTA, a novel lightweight temporal adapter that efficiently compresses long video sequences into compact, LLM-compatible visual prefix tokens through short-to-long-range temporal aggregation. For robust visual perception, we pretrain Sur40k, a surgical-specific ViViT-style video encoder on 40,000 minutes of public surgical videos to capture fine-grained spatio-temporal procedural priors. Hi-GaTA employs a temporal pyramid with text-conditioned dual cross-attention, and improves multi-scale consistency through cross-level gated fusion and an increasing-depth strategy. Finally, we fine-tune the LLM backbone using LoRA to enable coherent and stylistically consistent surgical report generation under limited supervision. Experiments show our approach achieves the best overall performance, with consistent gains over strong Multimodal Large Language Model (MLLM) baselines. Ablation studies further validate the effectiveness of each proposed component.

Kedi Sun, Chaohui Dang, Yue Feng +3

School of Engineering, College of Engineering and Physical Sciences, University of Birmingham, Birmingham, UK · School of Computer Science, University of Birmingham, Birmingham, UK · Department of Applied Health Sciences, University of Birmingham, Birmingham, UK

Surgical Videos Video Temporal Grounding Long Visual-Token Sequences Spatial Priors Global Average Pooling

May 11, 2026cs.LG

The Truth Lies Somewhere in the Middle (of the Generated Tokens)

How should hidden states generated autoregressively be collapsed into a representation that reflects a language model's internal state? Despite tokens being generated under causal masking, we find that mean pooling across their hidden states yields more semantic representations than any individual token alone. We quantify this through kernel alignment to reference spaces in language, vision, and protein domains. The improvement through mean pooling is consistent with information being distributed across generated tokens rather than localized to a single position. Furthermore, representations derived from generated tokens outperform those from prompt tokens, and alignment across generation reveals interpretable dynamics in model behavior.

Sophie L. Wang, Phillip Isola, Brian Cheung

1MIT.

Global Average Pooling Semantic Representations Medium Truth

May 9, 2026cs.CV

RigidFormer: Learning Rigid Dynamics using Transformers

Learning-based simulation of multi-object rigid-body dynamics remains difficult because contact is discontinuous and errors compound over long horizons. Most existing methods remain tied to mesh connectivity and vertex-level message passing, which limits their applicability to mesh-free inputs such as point clouds and leads to high computational cost. Efficiently modeling high-fidelity rigid-body dynamics from mesh-free representations, therefore, remains challenging. We introduce RigidFormer, an object-centric Transformer-based model that learns mesh-free rigid-body dynamics with controllable integration step sizes. RigidFormer reasons at the object level and advances each object through compact anchors; Anchor-Vertex Pooling enriches these anchors with local vertex features, retaining contact-relevant geometry without dense vertex-level interaction. We propose Anchor-based RoPE to inject anchor geometry into attention while respecting the unordered nature of objects and anchors: object-token processing is permutation-equivariant, and the mean-pooled anchor descriptor is invariant to anchor reindexing while preserving shape extent. RigidFormer further enforces rigidity by projecting updates onto the rigid-body manifold using differentiable Kabsch alignment. On standard benchmarks, RigidFormer outperforms or matches mesh-based baselines using point inputs, runs faster, generalizes to unseen point resolutions and across datasets, and scales to 200+ objects; we also show a preliminary extension to command-conditioned articulated bodies by treating body parts as interacting object-level components.

Zhiyang Dou, Minghao Guo, Haixu Wu +3

MIT · Meta

Rigid-Body Dynamics Transformer Architectures Global Average Pooling

May 8, 2026cs.LG

Embedding Dimension Lower Bounds for Universality of Deep Sets and Janossy Pooling

In many practical applications it is important to build symmetries into neural network architectures. Consider the important case of permutation symmetry on point clouds consisting of

n

points in

d

dimensions. In this case the network learns a function on a set of

n

points in

\mathbb{R}^d

, and a natural paradigm for constructing invariant networks is Janossy pooling, which generalizes the popular Deep Sets architecture. We study the universality of this approach, in particular the important question of how large the embedding dimension must be to guarantee universality of this architecture. Specifically, using a novel technique, we prove new lower bounds on the required size of this embedding dimension. For Deep Sets, this gives the correct minimal dimension up to a constant factor for all

d > 1

. For

k

-ary Janossy pooling, we prove the first non-trivial lower bound on the required embedding dimension when

k > 1

.

Ali Syed, Aditya Nambiar, Jonathan W. Siegel

Department of Mathematics Texas A&M University College Station, TX 77843

Intrinsic Dimensionality Behavioral Embeddings Equivariant Neural Networks Global Average Pooling Lower Bounds

May 8, 2026cs.CV

UIESNN: A Scale-Aware Spiking Network for Underwater Image Enhancement

Underwater image enhancement (UIE) is a practically important yet underexplored application of spiking neural networks (SNNs), where the dominant degradations are large-scale and low-frequency, such as wavelength-dependent colour casts and scattering-induced veiling. Existing SNN restoration designs rely on locally bounded spiking perception, which can limit global correction and lead to saturated or inconsistent representations. To address these challenges, we propose a scale-aware SNN framework for UIE named UIESNN. At its core is a Multi-scale Pooling LIF Block (MPLB) that injects hierarchical multi-scale pooling responses into membrane dynamics, thereby enlarging the effective receptive field while preserving fine-grained details and inducing heterogeneous scale-dependent activations. Building on MPLB, we design a spiking residual architecture that integrates frequency decomposition and attention-based refinement in a fully spike-driven pipeline. Extensive experiments on the EUVP and LSUI benchmarks demonstrate that UIESNN achieves state-of-the-art performance among SNN-based methods, delivering improved colour fidelity and spatial coherence with competitive energy cost.

Shuang Chen, Ruochen Li, Zihan Zhu +3

Computer Science Department, Durham University, UK · University of Cambridge · Institute of Biology, University of Graz, Graz, Austria.

Spiking Neural Networks Underwater Image Enhancement Methods Time-To-First-Spike Multi-Scale Convolution Receptive Fields Enhancement+1

May 8, 2026cs.LG

bispectrum: Selective $G$ -Bispectra Made Practical

Many machine learning tasks are invariant under the action of a group

G

of transformations: signal classification can be invariant under translations, image classification under 2D rotations, and spherical-image classification under 3D rotations. The

G

-bispectrum is a principled complete invariant of a signal (retaining all all signal's information up to the group action) with proven benefits in machine learning and as a pooling layer in deep networks. However, its deployment has been hampered by high computational cost and a patchwork of group-specific implementations. We present bispectrum, an open-source, fully unit-tested PyTorch library that implements selective

G

-bispectra for seven different group actions, as differentiable modules that can be directly incorporated into machine learning pipelines and deep learning architectures. For finite groups

G

, selectivity reduces the computational cost from

O(|G|^2)

to

O(|G|)

. For planar rotations, we leverage the disk bispectrum. For spherical 3D rotations, we introduce an augmented selective bispectrum at band-limit

L

which reduces the cost from

O(L^3)

to

Θ(L^2)

coefficients. We profile the entire library (for which we implemented various compute optimizations), showing that it delivers near-exact

G

-invariance with its selective

G

-bispectra computed in sub-millisecond time on GPU (up to commonly used bandlimits). We evaluate the benefits of incorporating

G

-bispectra as pooling layers into deep learning architectures on three classical benchmark datasets --comparing against norm pooling, gated pooling, Fourier-ELU pooling, max pooling, and (non-equivariant) data-augmented convolutional baselines. Results show that

G

-bispectra consistently outperform alternatives in the low-data, moderate-capacity regime.

Johan Mathe, Adele Myers, Simon Mataigne +1

Atmo, Inc. San Francisco, CA · UC Santa Barbara Santa Barbara, CA · UCLouvain Louvain-la-Neuve, Belgium

Global Average Pooling Spherical Latent Space Spectral Deep Learning Selectivity Selective

May 7, 2026cs.LG

The Role of Node Features in Graph Pooling

Graph pooling is commonly applied in graph classification, yet its empirical gains over standard WL-1 expressive GNNs are often marginal or inconsistent. We study this gap by analysing the interaction between node features and graph topology and their effect on pooling objectives. Our analysis reveals that pooling operators require node features that are well-aligned with the graph's topology -- a condition often overlooked and not guaranteed in empirical networks. We formalise fundamental requirements for node features to enable effective pooling, and introduce a quantitative measure of feature quality. Our empirical evaluation shows that, when these requirements are satisfied, pooling can be beneficial and improve performance on appropriate datasets.

Jan von Pichowski, Alžbeta Hrabošová, Ingo Scholtes +1

Center for AI and Data Science University of Würzburg, Germany · Department of Computing Science Umeå University, Sweden

Graph Neural Networks Global Average Pooling Network Science Role

May 5, 2026cs.SD

PHALAR: Phasors for Learned Musical Audio Representations

Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal information. We introduce PHALAR, a contrastive framework achieving a relative accuracy increase of up to

\approx 70\%

over the state-of-the-art while requiring

<50\%

of the parameters and a 7

\times

training speedup. By utilizing a Learned Spectral Pooling layer and a complex-valued head, PHALAR enforces pitch-equivariant and phase-equivariant biases. PHALAR establishes new retrieval state-of-the-art across MoisesDB, Slakh, and ChocoChorales, correlating significantly higher with human coherence judgment than semantic baselines. Finally, zero-shot beat tracking and linear chord probing confirm that PHALAR captures robust musical structures beyond the retrieval task.

Davide Marincione, Michele Mancusi, Giorgio Strano +4

Department of Computer Science, Sapienza University of Rome, Italy · Moises Systems, Inc. · Paradigma, Inc.

Music Structure Analysis Global Average Pooling Contrastive Learning

Apr 30, 2026cs.CV

Parameter-Efficient Architectural Modifications for Translation-Invariant CNNs

Convolutional Neural Networks (CNNs) are widely assumed to be translation-invariant, yet standard architectures exhibit a startling fragility: even a single-pixel shift can drastically degrade performance due to their reliance on spatially dependent fully connected layers. In this work, we resolve this vulnerability by proposing a lightweight 'Online Architecture' strategy. By strategically inserting Global Average Pooling (GAP) layers at various network depths, we effectively decouple feature recognition from spatial location. Using VGG-16 as a primary case study, we demonstrate that this architectural modification achieves a massive 98% reduction in trainable parameters (from 5.2M to just 82K) and a 90% reduction in total network size (138M to 14M). Despite this drastic pruning, our variants maintain competitive Top-1 accuracy on ImageNet (66.4%) while doubling translational robustness, reducing average relative loss from 0.09 to 0.05. Furthermore, our analysis identifies a fundamental limit to invariance: while GAP resolves macroscopic sensitivity, discrete pooling operations introduce a residual periodic aliasing that prevents perfect pixel-level stability. Finally, we extend these findings to Perceptual Image Quality Assessment (IQA) by integrating our invariant backbones into the LPIPS framework. The resulting metric significantly outperforms the retrained baseline in generalization across the KADID-10k dataset (Spearman 0.89 vs. 0.75) and achieves a near-perfect alignment with human psychophysical response curves on the RAID dataset (Spearman 0.95). These results confirm that enforcing architectural invariance is a far more efficient and biologically plausible path to robustness than traditional data augmentation. Data and code are publicly available. The data and code are publicly available to facilitate validation and further research.

Nuria Alabau-Bosque, Jorge Vila-Tomas, Paula Dauden-Oliver +2

Image Processing Lab, Universitat de València, Carrer del Catedr´atic Jos´e Beltr´an Martinez, Paterna, 46980, Spain.

Convolutional Neural Networks Global Average Pooling Pixels

Apr 30, 2026cs.CL

Why Mean Pooling Works: Quantifying Second-Order Collapse in Text Embeddings

For constructing text embeddings, mean pooling, which averages token embeddings, is the standard approach. This paper examines whether mean pooling actually works well in real models. First, we note that mean pooling can collapse information beyond the first-order statistics of the token embeddings, such as second-order statistics that capture their spatial structure, potentially mapping distinct token embedding distributions to similar text embeddings. Motivated by this concern, we propose a simple metric to quantify such a collapse induced by mean pooling. Then, using this metric, we empirically measure how often this collapse occurs in actual models and texts, and find that modern text encoders are robust to this collapse. In particular, contrastive fine-tuned text encoders tend to be less prone to the collapse than their pretrained backbone models. We also find that the robustness of these text encoders lies in the concentration of token embeddings within each text. In addition, we find that robustness to the collapse, as quantified by our proposed metric, correlates with downstream task performance. Overall, our findings offer a new perspective on why modern text encoders remain effective despite relying on seemingly coarse mean pooling.

Tomomasa Hara, Hiroto Kurita, Masaaki Imaizumi +2

Tohoku University · The University of Tokyo · Kyoto University +3

Token Embeddings Text Embeddings Global Average Pooling Encoders Collapse Text Analysis and Detection+1

Sep 17, 2025cs.LG

FedIA: Importance-Aware Aggregation for Domain-Robust Federated Graph Learning

Federated graph learning (FGL) is a natural paradigm for social-media user graphs, where language communities, regional markets, and service boundaries can prevent raw graph pooling. We use the Twitch Gamers networks as the primary live-streaming social-media benchmark, and study a question that is often hidden by representation-level evaluation: after local message passing, what update signals are actually exposed to server aggregation? Through update-space measurements, we identify an aggregation-level failure in which graph-domain clients gradually place salient update signals on less shared parameter coordinates, while message-passing backbones show weaker cross-domain directional compatibility than an MLP control. This update-support fragmentation means that standard averaging can dilute locally important coordinates even when no raw graph data are exchanged. Across five backbones, homophily remains relevant but is not the dominant correlate of support retention; feature, label, and degree discrepancies show stronger associations. These findings indicate that graph-domain shifts damage not only local representations, but also the coordinate support on which aggregation operates. Motivated by this diagnosis, we propose FedIA, a plug-and-play server-side importance-aware aggregation method. Importance Masking selects a shared high-magnitude coordinate support, and Contribution-Aware Momentum Weighting smooths client contributions within that support. FedIA requires no raw graph sharing, no graph-statistics upload, and no auxiliary communication payload, while adding only

O(D+N)

persistent server state for

D

model coordinates and

N

clients.

Zhanting Zhou, Zeyu Ma, Ziqiang Zheng +1

University of Electronic Science and Technology of China, No. 2006, Xiyuan Ave, West Hi-Tech Zone, Chengdu, Sichuan 611731, China

Federated Graph Learning Fedavg Global Average Pooling Mitigating Domain Shift

May 10, 2023cs.CG

NervePool: A Simplicial Pooling Layer

For deep learning problems on graph-structured data, pooling layers are important for down sampling, reducing computational cost, and to minimize overfitting. We define a pooling layer, nervePool, for data structured as simplicial complexes, which are generalizations of graphs that include higher-dimensional simplices beyond vertices and edges; this structure allows for greater flexibility in modeling higher-order relationships. The proposed simplicial coarsening scheme is built upon partitions of vertices, which allow us to generate hierarchical representations of simplicial complexes, collapsing information in a learned fashion. NervePool builds on the learned vertex cluster assignments and extends to coarsening of higher dimensional simplices in a deterministic fashion. While in practice the pooling operations are computed via a series of matrix operations, the topological motivation is a set-theoretic construction based on unions of stars of simplices and the nerve complex.

Sarah McGuire Scullen, Ernst Röell, Elizabeth Munch +2

Pacific Northwest National Lab, USA · Helmholtz Munich and Technical University of Munich, Germany · Michigan State University, USA +1

Global Average Pooling Simplex Neuroflex