Overview

Feature attribution studies how to assign responsibility for a model’s prediction to parts of its input, such as image regions, text tokens, time-series measurements, or graph features. Common approaches include gradients and relevance propagation, perturbation and masking, Shapley values, and counterfactual or causal interventions; some methods instead build explanations into the model. Researchers evaluate explanations for faithfulness, stability, sparsity, localization, and usefulness across tasks such as image classification, language modeling, medical prediction, and time-series forecasting. A central challenge is that attributions can change with the model architecture, baseline, perturbation choices, or correlations among features, so no single method or metric is reliable in every setting.

Latest papers

253 papers21 papers in the last four weeks, up 5% on the four weeks before. 0.2% of all new papers.

Feb 18, 2026

Functional Decomposition and Shapley Interactions for Interpreting Survival Models

Hazard and survival functions are natural, interpretable targets in time-to-event prediction, but their inherent non-additivity fundamentally limits standard additive explanation methods. We introduce Survival Functional Decomposition (SurvFD), a principled approach for analyzing feature interactions in machine learning survival models. By decomposing higher-order effects into time-dependent and time-independent components, SurvFD offers a previously unrecognized perspective on survival explanations, explicitly characterizing when and why additive explanations fail. Building on this theoretical decomposition, we propose SurvSHAP-IQ, which extends Shapley interactions to time-indexed functions, providing a practical estimator for higher-order, time-dependent interactions. Together, SurvFD and SurvSHAP-IQ establish an interaction- and time-aware interpretability approach for survival modeling, with broad applicability across time-to-event prediction tasks.
Jan 19, 2026

Explanation Multiplicity in SHAP: Characterization and Assessment

SHAP explanations are widely used in high-stakes settings to justify decisions, yet they can differ substantially across repeated runs, even when the model, the input instance, and the prediction are held fixed. Prior work has documented disagreement between explanation methods; we show that substantial disagreement arises even within SHAP across reruns of the same estimator on the same trained model and instance. We call this phenomenon explanation multiplicity and develop an evaluation methodology for characterizing it under deployment-realistic computational budgets, combining a dual-seed protocol that compares model-induced and explainer-induced variability, a hierarchy of magnitude-based, rank-based, and set-based metrics, and randomized Dirichlet and Mallows null models that provide reference scales for observed disagreement. Across multiple datasets, models, and sampling strategies, we find that explanation multiplicity is pervasive and persists even for high-confidence predictions. The relative contribution of each source depends on the data regime and model: model-induced disagreement is generally greater on smaller datasets, while explainer-induced disagreement is greater on larger datasets. Commonly used L2 distance can understate this instability, while rank-based metrics reveal substantial changes in top-ranked features, including the leading feature. Improved sampling methods such as CTE do not eliminate rank-level multiplicity, and K-Means reduces run-to-run variation while its compressed-background explanations can diverge from the empirical-distribution reference. Practitioners should treat single-run SHAP outputs as realizations of a distribution rather than as authoritative artifacts.
Jan 13, 2026

Motion Attribution for Video Generation

Despite the rapid progress of video generation models, the role of data in influencing motion is poorly understood. We present Motive (MOTIon attribution for Video gEneration), a motion-centric, gradient-based data attribution framework that scales to modern, large, high-quality video datasets and models. We use this to study which fine-tuning clips improve or degrade temporal dynamics. Motive isolates temporal dynamics from static appearance via motion-weighted loss masks, yielding efficient and scalable motion-specific influence computation. On text-to-video models, Motive identifies clips that strongly affect motion and guides data curation that improves temporal consistency and physical plausibility. With Motive-selected high-influence data, our method improves both motion smoothness and dynamic degree on VBench, achieving a 74.1% human preference win rate compared with the pretrained base model. To our knowledge, this is the first framework to attribute motion rather than visual appearance in video generative models and to use it to curate fine-tuning data.
Jan 10, 2026

Explainability of Complex AI Models with Correlation Impact Ratio

Complex AI systems make better predictions but often lack transparency, limiting trustworthiness, interpretability, and safe deployment. Common post hoc AI explainers, such as LIME, SHAP, HSIC, and SAGE, are model agnostic but are too restricted in one significant regard: they tend to misrank correlated features and require costly perturbations, which do not scale to high dimensional data. We introduce ExCIR (Explainability through Correlation Impact Ratio), a theoretically grounded, simple, and reliable metric for explaining the contribution of input features to model outputs, which remains stable and consistent under noise and sampling variations. We demonstrate that ExCIR captures dependencies arising from correlated features through a lightweight single pass formulation. Experimental evaluations on diverse datasets, including EEG, synthetic vehicular data, Digits, and Cats-Dogs, validate the effectiveness and stability of ExCIR across domains, achieving more interpretable feature explanations than existing methods while remaining computationally efficient. To this end, we further extend ExCIR with an information theoretic foundation that unifies the correlation ratio with Canonical Correlation Analysis under mutual information bounds, enabling multi output and class conditioned explainability at scale.
Nov 22, 2025

Matching-Based Few-Shot Semantic Segmentation Models Are Interpretable by Design

Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely opaque. Explainable AI has matured on standard computer vision tasks, but not on FSS, where an explanation would tell a practitioner which support pixels the prediction rested on and which examples to provide next. We argue that matching-based FSS models are interpretable by design: their query-support similarity scores, once normalized and processed, attribute the prediction to individual support pixels. Our approach, Affinity Explainer (AffEx), makes this intrinsic interpretability explicit by extracting attribution maps directly from matching scores at multiple feature levels, without requiring gradients or external perturbations. We extend the standard causal metrics for evaluating explanations to the FSS domain and propose additional metrics to better capture the practical utility of explanations in few-shot scenarios. Experiments on two FSS benchmarks, covering seven architectures that range from classical matching-based models to recent pipelines built on vision foundation models (DINOv2/v3, SAM, SAM2) and a prototype-based head, show that AffEx outperforms adapted standard attribution methods at nearly every evaluation point, and that the gain comes from the matching mechanism itself. On pipelines whose segmentation stage transforms the matching output, the same evaluation doubles as a diagnostic of where the decision is made, and on the prototype-based head AffEx subsumes the prototype-style read-out as a special case. Qualitatively, the attribution maps expose how each architecture resolves the support set, and we show how they guide model diagnosis. Code is available at https://github.com/pasqualedem/AffinityExplainer.
Nov 19, 2025

CID: Measuring Feature Importance Through Counterfactual Distributions

Assessing the importance of individual features in Machine Learning is critical to understand the model's decision-making process. While numerous methods exist, the lack of a definitive ground truth for comparison highlights the need for alternative, well-founded measures. This paper introduces a novel post-hoc local feature importance method called Counterfactual Importance Distribution (CID). We generate two sets of positive and negative counterfactuals, model their distributions using Kernel Density Estimation, and rank features based on a distributional dissimilarity measure. This measure, grounded in a rigorous mathematical framework, satisfies key properties required to function as a valid metric. We showcase the effectiveness of our method by comparing with well-established local feature importance explainers. Our method not only offers complementary perspectives to existing approaches, but also improves performance on faithfulness metrics (both for comprehensiveness and sufficiency), resulting in more faithful explanations of the system. These results highlight its potential as a valuable tool for model analysis. Link to repository: https://github.com/EddieConti/CID
Oct 26, 2025

Data-driven Sensor Placement for Predictive Applications: A Correlation-Assisted Attribution Framework (CAAF)

Optimal sensor placement (OSP) is critical for efficient, accurate monitoring, control, and inference in complex physical systems. We propose a machine-learning-based feature attribution (FA) framework to identify OSP for target predictions. FA quantifies input contributions to a model output; however, it struggles with highly correlated input data often encountered in practical applications for OSP. To address this, we propose a Correlation-Assisted Attribution Framework (CAAF), which introduces a clustering step on the candidate sensor locations before performing FA to reduce redundancy and enhance generalizability. We first illustrate the core principles of the proposed framework through a series of validation cases, then demonstrate its effectiveness in realistic dynamical systems such as structural health monitoring, airfoil lift prediction, and wall-normal velocity estimation for turbulent channel flow. The results show that the CAAF outperforms alternative approaches that typically struggle due to the presence of nonlinear dynamics, chaotic behavior, and multi-scale interactions, and enables the effective application of FA for identifying OSP in real-world environments.
Sep 26, 2025

Evidence Recomposition and Predictive Context Residualization for Visual Attribution in Multimodal Large Language Models

Multimodal large language models (MLLMs) have achieved strong vision-language performance, yet their token-level visual evidence remains difficult to inspect. Recent logit-lens attribution methods project each visual-token hidden state into the vocabulary space to explain generated words, but this token-wise readout introduces a mismatch: visual tokens are context-mixed by the model, while the attribution score is decoded independently at each token location. This often produces fragmented attribution maps and can be further affected by autoregressive context signals from preceding text tokens. We propose ERCR, an attribution framework built from Evidence Recomposition (ER) and Predictive Context Residualization (PCR). ER aggregates target evidence across multiple views with different token-to-region assignments, reducing attribution fragmentation caused by a single readout grid. PCR estimates a preceding-token context map with RBO-based rank relevance and subtracts its fitted component from the ER map to suppress context-token interference. Experiments on LLaVA, Qwen2-VL, and InternVL families across COCO Caption, GranDf, and OpenPSG show that ERCR improves visual evidence for target tokens and mitigates preceding-token context interference under the existing evaluation protocol. On Qwen2-VL-2B, ERCR improves TAM F1-IoU from 39.10 to 44.45 on COCO Caption and from 30.83 to 37.20 on GranDf. Overall, ERCR provides a practical refinement for token-level visual evidence inspection.
Sep 25, 2025

Frequency-Aware Model Parameter Explorer: A new attribution method for improving explainability

State-of-the-art attribution methods such as AttEXplore rely on adversarial sample generation that applies an all-pass filter across the frequency spectrum: they perturb all frequencies of the input image alike, from the low frequencies that carry coarse shape to the high frequencies that carry edges and textures. However, models rely on low and high frequencies to different degrees, and such an all-pass perturbation cannot adapt to the model being explained, which limits the faithfulness of the resulting attribution maps. We propose FAMPE (Frequency-Aware Model Parameter Explorer), an attribution method that overcomes this limitation by perturbing the low- and high-frequency bands of the input independently, so that the perturbation can be shifted toward the band that matters for the model. The boundary between the two bands is set for each image automatically from its spectral energy. On ImageNet with five convolutional neural network and Vision Transformer architectures, FAMPE significantly improves the Insertion Score over the strongest baseline, AttEXplore, on four of them, by up to 15.4%, at essentially the same computational cost. How the perturbed frequency bands are weighted matters: the best and the worst balance between them differ by 19-36% in Insertion Score, and the best balance depends on the architecture. Choosing the balance for each image with a probe that needs no ground truth raises the Insertion Score significantly further on all five architectures, reaching up to 24.4% above AttEXplore. Controlling which frequency band is perturbed is therefore a simple, low-cost way to improve attribution faithfulness.
Jul 30, 2025

Pulling Back the Curtain on Deep Networks

In linear models, visualizing a weight vector naturally reveals the model's preferred input direction, but extending this intuition to deep networks via gradients or GradientAscent often yields brittle or adversarial-looking features. We argue that deep networks are better understood as input-conditioned affine operators, whose natural adjoint action pulls a neuron's preferred direction back to input space. We further refine this representation through optional backward-only softening for hard-gated layers and propose pullbacks as an alternative backward operator for existing explanation procedures, including local attribution, smoothing, and iterative ascent. Across convolutional architectures (ResNet50, VGG) and transformer-based models (PVT), replacing gradients with pullbacks yields improvements in 46 out of 60 comparisons across five faithfulness, stability, and localisation metrics. In particular, PullbackAscent improves mean scores over GradientAscent across all five primary metrics on each architecture, reducing mean Infidelity by factors of 2.8 to 5.5. Strikingly, it also produces sharp, perceptually aligned and target-specific perturbations in only a few steps, without post-processing or explicit perceptual priors. More broadly, pullback-based methods achieve the best mean in 13 out of 15 architecture-metric combinations, outperforming established attribution baselines. Our results suggest that adjoint transport can serve as a reusable backward primitive, enhancing existing explanation procedures without architectural changes or elaborate attribution pipelines. We use "Semantic Pullbacks" (SP) to denote the resulting family of pullback-based explanations.
May 21, 2025

Explainable embeddings with Distance Explainer

While eXplainable AI (XAI) has advanced significantly, few methods address interpretability in embedded vector spaces where dimensions represent complex abstractions. We introduce Distance Explainer, a novel method for generating local, post-hoc explanations of embedded spaces in machine learning models. Our approach adapts saliency-based techniques from RISE to explain the distance between two embedded data points by assigning attribution values through selective masking and distance-ranked mask filtering. We evaluate Distance Explainer on cross-modal embeddings (image-image and image-caption pairs) using established XAI metrics including Faithfulness, Sensitivity/Robustness, and Randomization. Experiments with ImageNet and CLIP models demonstrate that our method effectively identifies features contributing to similarity or dissimilarity between embedded data points while maintaining high robustness and consistency. We also explore how parameter tuning, particularly mask quantity and selection strategy, affects explanation quality. This work addresses a critical gap in XAI research and enhances transparency and trustworthiness in deep learning applications utilizing embedded spaces.
Apr 1, 2025

Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection

To develop a trustworthy AI system, it is essential to understand its behavior using attribution methods, which aim to identify the input regions that most influence the model's decisions. For discrete inputs such as images, however, accurately identifying input-prediction interactions is particularly challenging because of combinatorial explosion. We formulate black-box attribution as an ordered interpretable subset-selection problem. Inspired by the marginal-gain principle of submodular optimization, the formulation permits redundancy, positive complementarity, and negative interference among input sub-regions. We propose LiMA (Less input is More faithful for Attribution), which ranks sub-regions by their contributions along a sequence of selected subsets. LiMA employs a composite objective that evaluates subsets through semantic consistency, collaboration, prediction confidence, and semantic effectiveness. We further design a bidirectional greedy search to efficiently identify important and non-critical sub-regions. Experiments on eight foundation models (CLIP, ImageBind, LanguageBind, QuiltNet, etc.) and six datasets (ImageNet, VGG-Sound, CUB-200-2011, etc.) demonstrate strong generalization and faithful interpretations with fewer sub-regions. LiMA achieves state-of-the-art Insertion, Deletion, and average highest confidence, with average improvements of 36.3% in Insertion and 39.6% in Deletion; it is also 1.6 times faster than naive greedy search. For failure attribution on incorrect predictions, LiMA improves average highest confidence by 86.1% over state-of-the-art methods. The code is available at https://github.com/RuoyuChen10/LIMA.
Jun 17, 2024

CHAOSMINING: Benchmarking Post-Hoc Attribution with Sparse Informative Features in High Dimensions

Post-hoc attribution is widely used to identify important model inputs, but evaluating whether these attributions identify truly informative features is difficult because real datasets rarely provide reliable ground truth. We introduce a multimodal benchmark containing symbolic tabular, vision, and audio tasks with known informative feature sets. In the main benchmark conditions, informative variables, spatial regions, or channels occupy fixed input coordinates while the remaining inputs provide irrelevant or distracting information. We use the benchmark to study how attribution quality depends on predictive performance, irrelevant-feature burden and structure, model configuration, and attribution mechanism, while separately measuring identification, stability, and computational cost. In most symbolic-data sweeps, informative-set identification co-varies with predictive performance, while the relative ordering of attribution methods remains largely stable. Across modalities, no method dominates all architectures and conditions, and greater attribution complexity does not consistently improve identification. Simple gradient attribution is often competitive at lower computational cost, while the vision and audio results show that architecture and the form of irrelevant content materially affect attribution quality.