Adaptive Loss Weighting

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 33% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 69

Oct 8, 2026cs.AI

MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation

On-policy distillation (OPD) trains a student on its own generated responses using token-level teacher supervision. However, uniform weighting overlooks differences in token learning value, while existing weighting methods rely on predefined mappings from prediction signals to token weights. These mappings are not learned from the effectiveness of the resulting student updates, limiting their ability to adapt to evolving learning needs. In this paper, we propose MetaOPD, a bilevel optimization framework that jointly learns the student model and a lightweight token-weighting network. The inner objective updates the student through weighted OPD, while the outer objective optimizes the weighting network using validation loss on reference solutions after a virtual student update. Differentiating through this update connects weighting decisions to their effects on post-update performance, allowing the mapping from prediction signals to token weights to evolve alongside the student. Experiments on six mathematical reasoning and three out-of-domain datasets, covering two student scales and seven baselines, demonstrate the effectiveness of MetaOPD, with Avg@8/Pass@8 gains over OPD of 1.99/5.97 percentage points for the 0.6B student and 2.25/6.41 points for the 1.7B student.

Zipeng Wang, Xinpeng Dong, Yuefan Wang +6

East China Normal University · Zhejiang University · The Chinese University of Hong Kong, Shenzhen

On-Policy Distillation Adaptive Loss Weighting Meta-Learning

Oct 8, 2026cs.CV

DLC: A Metric-Guided Dynamic Loss Controller for Multi-Objective Training

In this paper, we introduce a metric-guided dynamic loss controller (DLC) for multi-objective image restoration. Conventional image restoration pipelines usually train with a fixed weighted combination of multiple losses, without changing the relative importance of fidelity, perceptual similarity, and no-reference quality during optimization. DLC is an architecture- and loss-term-agnostic training-time controller: it does not modify the restoration architecture or introduce new differentiable loss terms, but dynamically reweights the existing training losses. During training, DLC periodically evaluates the current model on a small fixed feedback subset and uses the resulting quality metrics to update the loss-weight vector through an LLM-based controller. Because DLC operates on existing loss terms rather than task-specific architectures, the same controller formulation can be instantiated across diverse image restoration training pipelines. We evaluate DLC on three restoration domains: low-light image enhancement, deraining, and real-world super-resolution, using both reference-based and no-reference quality metrics. Across these settings, DLC considers metric-dependent trade-offs during optimization and guides training toward balanced operating points across fidelity and perceptual quality. The results show that DLC can move models toward more favorable operating points across different restoration domains, supporting its role as a practical plug-in controller for multi-objective image restoration.

Jaewan Ko, Janghoon Choi

Major in Data Science Convergence, Graduate School of Data Science Kyungpook National University, Daegu, Republic of Korea

Adaptive Loss Weighting Image Restoration

Oct 7, 2026cs.LG

Gen-PINNs: Generative Adversarial Physics Informed Neural Networks for solving partial differential equations

Physics-Informed Neural Networks (PINNs) are a widely used data-free method for solving Partial Differential Equations (PDEs) using machine learning. With recent advances in Generative Adversarial Networks (GANs), adversarial learning has shown strong capabilities for modeling complex data-driven problems; however, the use of GANs in deterministic physics-informed PDE solutions remains limited. In this work, we first identify limitations of standard PINNs for solving PDEs, including spectral bias, loss imbalance, and optimizer stagnation. We then propose Generative Adversarial Physics-Informed Neural Networks (Gen-PINNs), a unified deterministic residual-adversarial framework designed to improve data-free solutions of PDEs with sharp or shock-front behavior. The generator learns the underlying PDE solution using dynamically weighted physics-informed loss components, while separate discriminators evaluate complementary PDE residual features against ideal zero-residual states. The framework further develops and adapts several methodological components, including a Fourier representation for resolving high-frequency spatial content, an orthonormal spectral diagnostic for quantifying frequency-dependent solution errors, and a modified gradient-based dynamic weighting system for physics, initial-condition, boundary-condition, and adversarial loss objectives. Gen-PINNs is tested against standard PINNs on nonlinear and higher-order PDEs, including the Burgers, Allen-Cahn, and Kuramoto-Sivashinsky equations. The results demonstrate substantial improvements in accuracy and convergence across sharp-front, stiff, and higher-order PDE solutions, highlighting the potential of deterministic residual-adversarial learning as an effective approach for solving challenging nonlinear PDEs.

Muhammad M. Akmal, Kamy Sepehrnoori, Michael J. Pyrcz

Hilderbrand Department of Petroleum and Geosystems Engineering, The University of Texas at Austin · Department of Earth and Planetary Sciences, The University of Texas at Austin

PDE Solving Physics-Informed ML Generative Adversarial Networks Adaptive Loss Weighting

Oct 4, 2026cs.LG

Component-Level Evaluation of Adaptive PINN Training for CFD-Oriented Crystal Growth Simulation

Physics-informed neural network (PINN) training minimizes a weighted combination of partial differential equation (PDE), boundary-condition, and initial-condition losses. Because adaptive methods modify these weights during training, their weighted total losses are not always directly comparable. We compare fixed-weight PINN, gradient-normalized PINN (GNPINN), and a rule-based adaptive controller (AgenticPINN) under matched settings on a heat-equation benchmark and a simplified Czochralski-oriented thermal-fluid problem. In the crystal-growth MLP experiment, adaptive control reduced the PDE residual from the order of

10^{-5}

to

10^{-6}

, while the boundary-condition loss increased from the order of

10^{-5}

to

10^{-2}

. On the heat-equation benchmark, GNPINN achieved the lowest relative

L_2

field error (0.054), whereas AgenticPINN obtained the smallest PDE residual but a relative

L_2

error of 1.368. Gaussian-process surrogates were additionally evaluated using case-wise holdout tests on corrected Czochralski CFD parameter sweeps. The temperature-field error for the temperature sweep was approximately 6%, whereas the axial-velocity error for the crystal-rotation sweep was approximately 42%. These findings show that adaptive control can improve equation satisfaction while weakening other physical constraints. PINN training should therefore be evaluated using separate PDE, boundary-condition, and solution-error metrics rather than weighted total loss alone.

Niruta Chapagain, Rohit Raj, Bertwin Kurisinkal Shine +1

University of Europe for Applied Sciences Potsdam, Germany · Vienna, Austria · Technische Universität Chemnitz Chemnitz, Germany +1

Neural PDE Solvers PDE Surrogate Modeling Adaptive Loss Weighting Physics-Informed ML

Oct 1, 2026cs.CL

GAW-PO: Preference Optimization with Gradient-Aligned Token Weights

Most preference optimization methods, such as Direct Preference Optimization (DPO), apply preference supervision at the response level, although autoregressive language models are optimized token by token. As a result, all tokens in a rejected response contribute to the negative training signal, including tokens that may encode behavior that is useful for the preferred response. We introduce GAW-PO, a gradient-aligned token reweighting method for DPO that estimates, for each rejected token, whether penalizing it would interfere with the preferred update directions. Tokens whose gradients are strongly aligned with the preferred behavior receive a weaker negative contribution, while conflicting tokens retain a stronger penalty. Our method achieves the highest average performance among the evaluated preference-optimization methods, improving by 0.97 points over standard DPO and 0.65 points over the strongest competing baseline across 11 benchmarks spanning mathematics, reasoning, coding, and question answering. We further show that gradient-aligned weighting is substantially more robust to aggressive preference optimization: as the DPO regularization parameter

β

decreases, standard DPO degrades sharply, whereas GAW-PO continues to improve. These results suggest that accounting for the interaction between rejected-token updates and preferred behavior provides an effective form of token-level credit assignment for preference optimization.

Andreea Dutulescu, Stefan Ruseti, Mihai Masala +2

National University of Science and Technology POLITEHNICA Bucharest · NVIDIA

LLM Alignment Direct Preference Optimization Adaptive Loss Weighting Preference Optimization Preference-Based RL

Sep 27, 2026cs.CL

Rethinking Token Reweighting for SFT: Suppress, Reverse, and Extrapolate Learned Features

Supervised fine-tuning (SFT) learns most aggressively from tokens that the model deems least likely. This helps acquire new behaviors, but also amplifies noisy or conflicting supervision and can overwrite useful pretrained knowledge. Through a unified policy-loss view, we revisit existing token-reweighting methods and show that they assign nonnegative coefficients to demonstrated tokens. Consequently, they can suppress or amplify supervised updates, but cannot reverse harmful features once learned. Moreover, larger training weights do not amount to feature extrapolation, since they change the optimization trajectory rather than scale a fixed SFT direction. We argue that reversal and extrapolation require a stable reference frame defined by a fixed SFT delta. Motivated by this, we propose SCALE (Selective Control of Adaptation via Local Entropy), an entropy-guided adaptation-strength-control method that freezes the pretrained model and the SFT delta and learns bounded token- and module-specific gates by minimizing predictive entropy alone. These gates suppress, reverse, or extrapolate frozen SFT features according to their alignment with entropy reduction. Across Qwen2.5-Math-1.5B, Qwen2.5-Math-7B, and Qwen3-4B-Base, SCALE achieves mathematical-reasoning averages of 37.84, 43.60, and 36.57, exceeding the strongest corresponding baselines while remaining competitive on general-retention benchmarks. It also attains the best average code-generation performance across HumanEval, HumanEval+, and MBPP for all three models. These results suggest that effective SFT correction can benefit from controlling how already learned residuals are used, rather than only modifying how they are learned.

Cunchun Li, Haonan He, Yifan Gao +4

Shanghai AI Laboratory · University of Science and Technology of China · Fudan University +2

Supervised Fine-Tuning Adaptive Loss Weighting Selective Fine-Tuning LLM Reasoning

Sep 26, 2026cs.LG

Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL

ELBO-based reinforcement learning offers a sampler-agnostic approach to fine-tuning flow matching models with reward feedback. Timestep weighting in ELBO-based RL has large impact on performance, and it also provides a unified view (as we show in this work) to understand prediction losses heuristically chosen in prior work, yet it remains under-researched and is often chosen to inherit pretrain configs. We investigate impacts and dynamics of timestep weighting in ELBO-based RL. We show that effective weighting depends on both the reward landscape and stage of learning. (1) Through experiments on controlled CIFAR image generation, complemented by robotics, we investigate how weighting impacts reward-driven updates across noise levels. (2) Through gradient analysis, we reveal distinct patterns of cross-noise coordination across tasks and their evolution during training. These findings motivate the hypothesis that useful weighting depends on the gap between the policy's current behavior and the behavior favored by the reward. (3) Guided by this analysis, we study simple static weighting, budgeted profile selection, and dynamic schedules that improve performance beyond conventional target choices. Our results establish timestep weighting as an important design choice for flow-matching RL and motivate further research into methods that choose and adapt it throughout learning.

Qinwei Ma, Jingzhe Shi, Simin Fan +2

College of AI, Tsinghua University · Department of Electrical and Computer Engineering, Princeton University · EPFL +1

RL for Image Generation Adaptive Loss Weighting Flow-Based Generative Modeling RL for Generative Models

Sep 22, 2026cs.LG

FairMean: Promoting Fairness in Distributed Learning under Label Poisoning Attacks

Fairness-aware distributed learning prioritizes clients with large losses to reduce performance disparities, but label poisoning can create large losses, thereby inducing a fairness--robustness conflict. We propose FairMean to manage this conflict. FairMean weights client gradients using a bounded, nondecreasing function of local loss. The increasing weights prioritize high-loss clients to promote fairness, while the upper bound prevents excessive loss-induced amplification of poisoned-client gradients. In the absence of label poisoning, we show that minimizing the FairMean objective is more conducive to solution fairness than minimizing the standard average-loss objective. Under label poisoning, we establish an average-stationarity bound whose attack-dependent term is proportional to the square of the poisoned-client fraction. Experiments show that FairMean promotes fairness by reducing accuracy variance while improving worst-client accuracy.

Huigan Zheng, Jiaojiao Zhang, Yongxiang Liu

Sun Yat-Sen University · Pengcheng Laboratory · Great Bay University

Algorithmic Fairness Adaptive Loss Weighting Distributed Training Data Poisoning Attacks

Sep 12, 2026cs.LG

Adaptive Margin Ordinal Loss: Penalizing Center-Class Hedging in Ordinal Classification

Standard cross-entropy loss causes neural networks trained on ordinal classification tasks to hedge predictions toward center classes, a failure mode we term \emph{center-class hedging}. This occurs because predicting the middle class minimizes expected symmetric loss, making it the path of least resistance regardless of the true label. Existing ordinal losses address related problems such as large-error penalization and rank consistency, but none directly suppresses center-class hedging as a function of where the true label lies relative to the ordinal center. We propose the Adaptive Margin Ordinal Loss (AMOL), a multiplicative weight applied to per-class loss terms of the form

m(k,y) = 1 + \alpha \cdot (1 - |k-c|/c) \cdot (|y-c|/c)

, where

c

is the center class,

k

is the candidate class, and

y

is the true label. The weight encodes a joint condition: it is large only when the candidate class is near center and the true label is far from center, collapsing to standard behavior otherwise. We further introduce the Center-Hedging Rate (CHR) as a diagnostic metric that directly quantifies this failure mode. Across four ordinal classification benchmarks and five random seeds, AMOL achieves the best or tied-best Quadratic Weighted Kappa (QWK) on all four datasets compared to cross-entropy, OLL, and SORD baselines. An asymmetric variant (AMOL-asym) eliminates center-class hedging entirely on the Abalone dataset (

\text{CHR} = 0.000 \pm 0.000

across all five seeds,

n \approx 266

extreme-class test samples per run), compared to

0.074 \pm 0.005

for standard cross-entropy.

Manisha Kandel

Data Science Institute & Department of Civil, Construction & Environmental Engineering University of Delaware Newark, DE, USA

Ordinal Regression Adaptive Loss Weighting Classification

Sep 12, 2026cs.AI

A Unified Per-Token Gating Family for On-Policy Distillation: FKL/RKL Mixing with Multi-Channel and Bias Coefficients

Per-token gating of forward/reverse KL losses has become a standard technique for on-policy knowledge distillation (OPD), but existing methods such as EOPD (Jin et al., 2026) and ToDi (Jung et al., 2025) each fix a single gating signal and a single gating direction, and the two have never been compared directly. We introduce a four-coefficient parameterization lambda_t = sigma(a * h_t + b * u(x) + c + d * gap_t) in which direction-aligned proxies of EOPD and ToDi appear as one-dimensional (1D) restrictions, and which adds multi-channel composition and an explicit bias as further degrees of freedom. On TweetEval (Barbieri et al., 2020) emotion and hate, with a Qwen3-32B teacher and a Qwen3-4B student, configurations in the full family reach higher accuracy than the matched-magnitude single-channel (entropy-only / gap-only) 1D restrictions in 33 of 36 comparable cells, and a 26-cell mean-match isolation experiment places dynamic gating ahead of effective-KL-matched static baselines in 19 of 26 cells. Because cells share training data, models, and parameter substructure, we report both counts as exploratory aggregate directional evidence rather than as independent hypothesis tests. Targeted three-seed paired replications of the nine headline comparisons singled out by that sweep -- including a third task, offensive -- are directionally consistent, but individually smaller than the single-seed estimates and not significant at n=3. We therefore present the parameterization primarily as a shared coordinate system for comparing per-token gating designs in short-output classification OPD.

Suwan Wu, Yumeng Lin, Pengcheng Yuan +1

Xiaohongshu Inc. · Tianjin University

Adaptive Loss Weighting Language Model Distillation On-Policy Distillation

Sep 9, 2026cs.AI

Which Tokens Should SFT Actually Learn? A Token-Trimming Perspective on Mathematical Reasoning

Supervised fine-tuning (SFT) applies a uniform cross-entropy loss to all target tokens, even though different tokens provide unequal learning signals for mathematical reasoning. This uniform treatment can over-sharpen already mastered tokens while amplifying learning pressure on uncertain, low-confidence tokens, leading to suboptimal training dynamics. We propose Trimmed Logit-Gap SFT (TrimSFT), a simple token-level reweighting method that scales the SFT loss according to the logit gap between the gold token and its strongest competitor. TrimSFT trims supervision away from both extremes: tokens already mastered (large logit gap) and tokens weakly supported by the current model (small or negative logit gap), concentrating learning within an intermediate logit-gap region between them. We instantiate this principle with a Gaussian weight centered at margin m with bandwidth τ, requiring no reference model or additional forward pass. We evaluate TrimSFT on six base models from the Llama, Qwen, and DeepMath families across five mathematical reasoning benchmarks. TrimSFT consistently improves over standard SFT, achieving the best average performance on five out of six models, with gains of up to +26.9 points over SFT on MATH500. Further analyses show that the bandwidth τ matters more than the exact margin location, and that half-trim variants that remove supervision pressure from only one side yield inferior trade-offs. A token-level logit-gap distribution analysis suggests that TrimSFT reshapes model confidence in a more balanced way than uniform SFT or monotonic reweighting methods. These results suggest that reasoning SFT can benefit from trimming both extremes rather than treating all tokens uniformly.

Yaning Jia, Chunhui Zhang, Wenxuan Xu +3

Dartmouth College · Carnegie Mellon University

Numerical Reasoning in Language Models Supervised Fine-Tuning Adaptive Loss Weighting

Sep 3, 2026cs.RO

TRaIL-Odom: Tightly Coupled Continuous Time Radar-IMU-LiDAR Odometry with Adaptive Doppler Weighting

Existing radar-LiDAR fusion methods rely on fixed residual weights, even though the informativeness of radar Doppler and LiDAR geometry is scan- and direction-dependent, leading to uniform radar weighting that misallocates Doppler information across translational directions. To address this limitation, we propose two degeneracy-aware Doppler reweighting modules within a tightly coupled Radar-IMU-LiDAR odometry framework: per-point radar reweighting and scan-wise radar gain scheduling. Since geometric degeneracy is directional, we first identify weak translational directions from the LiDAR geometry and reweight individual radar Doppler constraints based on their alignment with the weak subspace. We further adjust the overall radar contribution using LiDAR geometric anisotropy such that radar is emphasized when LiDAR observability is poor and suppressed when LiDAR constraints are already reliable. Across 13 evaluated sequences, TRaIL-Odom achieves state-of-the-art overall performance, with clear advantages in geometrically degenerate scenes. In ablation experiments on three degenerate sequences, combining the two adaptive weighting modules reduces RMSE ATE and RTE by 86.0% and 78.5% relative to the fixed-weight baseline. We make our code and an accompanying dataset publicly available at https://github.com/ChiyunNoh/TRaIL-Odom.

Chiyun Noh, Turcan Tuna, William Talbot +3

Department of Mechanical Engineering, Seoul National University, S. Korea · Robotic Systems Lab (RSL), ETH Zürich, 8092 Zürich, Switzerland · Robotics and AI Institute (RAI), Zürich, Switzerland

Adaptive Loss Weighting Radar-Inertial Odometry Robot Localization Multimodal Sensor Fusion

Sep 2, 2026cs.CV

Information Density Imbalance in Visual Object Detection

In object detection, the number of instances is typically used to determine whether a dataset exhibits a long-tailed distribution, implicitly assuming that the model will perform poorly on categories with fewer instances. This assumption has led to extensive research on category bias in datasets with imbalanced instance numbers. However, even in datasets where instance numbers are relatively balanced, models still exhibit category bias, indicating that instance count alone cannot explain this phenomenon. In this work, we first introduce the concept and measurement of information density. We then observe a significant negative correlation between a category's information density and its accuracy, and we investigate how the training process impacts this relationship. Empirical studies suggest that information density imbalance may be a potential source of category bias. To preliminarily validate the potential of information density, we made simple improvements to three advanced object detection loss functions using this concept. Experiments on the Pascal VOC, COCO-LT, and LVIS datasets demonstrate that information density can significantly reduce model bias while effectively enhancing the overall performance of existing loss functions. This study provides a new perspective for understanding the generalized bias phenomenon in object detection models and offers new tools for designing fairer loss functions and training strategies.

Ziwei Zhao, Yanxi Lu, Yuwei Hu +8

Technical University of Munich · Nanyang Technological University · Baidu Inc. +3

Object Detection Adaptive Loss Weighting

Sep 1, 2026cs.LG

Online Self-Weighted Fine-Tuning

Standard supervised fine-tuning (SFT) assigns the same explicit loss weight to every expert demonstration, regardless of the model's changing competence over training queries. Reinforcement learning (RL) based methods adapt update strength using model-generated rollouts, but often require substantially more sampling and can be unstable on hard tasks. We propose \textbf{Online Self-Weighted Fine-Tuning (OSW-FT)}, a simple method that augments SFT with online, trajectory-level weighting. For each query, OSW-FT estimates the model's current success rate using a small number of inference-only rollouts and rescales the standard SFT loss accordingly. The optimization direction remains anchored to the expert trajectory, while the update magnitude adapts online. For binary-verifiable reasoning, we connect this weighting to SFT and RL at the gradient level, inspired by variance-reduction principles. The resulting estimator is unbiased for the exact OSW-FT surrogate update for any finite rollout count, and we analyze convergence with respect to the corresponding surrogate objective. Evaluated across Qwen3 series ranging from 0.6B to 4B on multiple challenging benchmarks (e.g., AIME), OSW-FT consistently improves over SFT on small-to-medium scale models. OSW-FT offers a favorable compute-performance trade-off as a practical approach for fine-tuning small-to-medium LLMs on binary-verifiable reasoning tasks with only \textbf{2 online rollouts}.

Haiquan Wen, Yiwei He, Bei Peng +1

University of Liverpool · University of Sheffield

Supervised Fine-Tuning LLM Fine-Tuning Adaptive Loss Weighting

Aug 31, 2026cs.CL

Error-Type-Aware Loss Reweighting for Robust Named Entity Recognition with Noisy LLM Labels

Large language models are increasingly used to annotate datasets for training smaller, task-specialized models such as named entity recognition. While this method yields effective models, it assumes that the synthetic dataset is correctly annotated. In this work, we find that (i) current fine-tuning processes simply ignore LLM-introduced annotation noise, resulting in degraded performance and (ii) existing noise-robust losses are not transferable to sequence labeling because annotation noise in named entity recognition is heterogeneous: for example, missing mentions and type errors affect the training signal in different ways. Treating all noisy tokens equally in noise-robust losses and applying a single reweighing criterion for all may therefore remove useful supervision or reinforce incorrect labels. To address this limitation, we propose error-type-aware loss reweighting for NER, which introduces separate reweighing rules for different types of potentially erroneous tokens. Our approach is simple and efficient, does not require additional training resources, and improves F1 by 0.8 - 2.0 percentage points on dataset-level average for noise levels between 15% and 40%, with a maximum improvement of 4.6 percentage points with 24.1% noise on Wikigold.

Elena Merdjanovska, Jonas Golde, Alan Akbik

Humboldt-Universität zu Berlin · Science of Intelligence

Named Entity Recognition LLM-Assisted Annotation Noisy-Label Learning Robust Loss Functions Adaptive Loss Weighting

Aug 27, 2026cs.CV

Tissue-Mixture Entropy-Weighted Reconstruction for Partial-Volume-Aware Brain MRI Super-Resolution

Background and Objectives: Full-image objectives in brain magnetic resonance imaging (MRI) super-resolution (SR) can underweight tissue-transition regions affected by the partial-volume effect (PVE), as these regions occupy a small fraction of the image. Binary boundaries further provide only a discrete approximation of continuous tissue mixtures within a voxel. Methods: We propose Anatomy-Guided Gaussian-Parameter Warping with PVE-Balanced Reconstruction (AGW-PBR), combining a low-resolution (LR)-only reconstruction backbone with a PVE-aware training objective. The backbone uses LR-derived anatomical guidance, soft latent assignment, and bounded residual warping. Quality-controlled tissue fractions are converted into tissue-mixture entropy to spatially weight reconstruction within validated PVE support. PVE sidecars are used only during training, while inference requires only the LR image. Downstream utility is further evaluated through zero-shot transfer to whole-tumor segmentation on BraTS2023. Results: AGW-PBR improves reconstruction across 2x and 4x SR on IXI and achieves the lowest normalized gradient-vector reconstruction error at both CSF--GM and GM--WM interfaces at 4x. Ablation studies verify the contributions of PVE-aware weighting and soft latent assignment. The PVE-free AGW backbone also maintains strong performance on fastMRI. On BraTS2023, AGW-PBR achieves competitive whole-tumor Dice and the lowest HD95 under direct zero-shot transfer. Conclusions:AGW-PBR improves brain MRI SR while preserving tissue-transition information relevant to downstream analysis. The results support tissue-mixture entropy as an effective supervision signal for partial-volume-aware MRI reconstruction.

Xiao Tong, Wenyun Yang, Ziheng Zhang +3

aState Key Laboratory of Artificial Microstructure and Mesoscopic Physics, School of Physics, Peking University, Beijing, 100871, P. R. China · bWeihai Institute of Oceanology, Peking University, Weihai, 264209, P. R. China · cBeijing MagnVue Medix Co., Ltd., Beijing, 100085, P. R. China

Medical Image Super-Resolution Brain MRI Adaptive Loss Weighting

Aug 10, 2026cs.LG

Confusion-Geometry Rebalancing for Long-Tailed Adversarial Training

Adversarial training under long tailed distributions suffers from a dual imbalance: the class imbalance skews the training objective toward head classes, and the adversarial inner maximization may further amplify this bias. Existing methods mitigate this issue by correcting class priors or adapting class wise robust supervision, yet they treat each class in isolation and fail to identify which boundaries drive long tailed collapse. We propose a Confusion Geometry Rebalancing method (CGRm) for long tail adversarial training, a plug in framework that leverages directed robust errors as training signals. CGRm leverages periodic robust evaluations to derive source class loss weights, class wise robust coefficients, and a directed confusion geometry graph. The method then couples feedback weighted robust optimization with graph guided margin correction, thereby boosting the robustness of vulnerable classes and sharpening the critical boundaries that drive long tailed performance degradation. Experiments on long tailed benchmarks show that CGRm achieves consistent robust performance gains over existing methods, with ablations validating the contribution of each component. We provide the code in the supplement.

Mengnan Zhao, Geyong Min, Lihe Zhang +2

School of Computer Science, Anhui University, China · Department of Computer Science, University of Exeter, UK · School of Information and Communication Engineering, Dalian University of Technology, China +1

Adversarial Training Long-Tailed Classification Adversarial Robustness Adaptive Loss Weighting

Aug 8, 2026cs.CV

NeuroGuard: Neural Gradient Update Aware of Representation Damage

Long-tailed class-incremental learning (LT-CIL) must learn new classes from imbalanced streams while retaining old classes. Existing methods mainly change replay, classifiers, or losses. We study a different factor, namely how strongly the feature representation should be updated at each task boundary. We propose NeuroGuard, an update-control method added to DGR, a replay-based LT-CIL baseline, without adding learnable parameters. NeuroGuard preserves DGR's replay memory, classifier, and set of loss terms. Adaptive Gradient Scaling (AGS) converts teacher uncertainty into one task-wise gradient scale. Confidence-Ranked Knowledge Distillation Reweighting (CRK) gives larger knowledge-distillation weights to replay samples that the teacher predicts less decisively. Fragility-Blended Entropy Gate (FBE) adds old-memory leakage to the scale decision. Across five LT-CIL settings, NeuroGuard improves over DGR in every setting. In the four main benchmark comparisons, it achieves the best task-agnostic accuracy among the compared methods. The gains extend to both old- and new-class accuracy, while medium-frequency accuracy improves consistently across all five settings. Controlled comparisons show that the gain does not come from generic gradient suppression: AGS outperforms a matched fixed-scale control in all five settings, demonstrating that boundary-specific scaling is more effective than applying the same average scale throughout learning.

Taigo Sakai, Kazuhito Hotta

Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan

Class-Incremental Learning Adaptive Loss Weighting Replay-Based Continual Learning Incremental Learning

Aug 8, 2026cs.CE

Tools to Explain Neural Networks for Power System Dynamics

This paper presents, for the first time in power systems literature to our knowledge, analytical tools to explain the training performance of machine learning surrogate models for power system dynamics. Power system simulations are increasingly challenged by stiff and multi-timescale dynamics arising from converter-interfaced resources and fast control loops. Machine learning surrogates emerge as promising tools to handle this complexity and accelerate dynamic simulations. However, their performance remains difficult to interpret, which limits their adoption. Building on the small-signal eigenvalue analysis in power systems, this paper uses the Neural Tangent Kernel (NTK) method. NTK delivers a modal interpretation of the learning performance, identifying error modes that decay rapidly versus others that converge slowly. This connection explains how physical stiffness and timescale separation in power system dynamic models appear as optimization stiffness during Neural Network (NN) training. Based on this analysis, we develop adaptive loss-weighting strategies to improve and explain why structure-aware neural architectures, such as ActNet, perform better than vanilla NNs. We assess the proposed approach on physics-informed machine learning surrogate models of \acp{SM} and power electronic converters. The methods introduced in this paper can deliver the necessary analytical tools to interpret and improve the performance of machine learning surrogates, paving the way for the systematic, physics-aware design of NN architectures and training strategies. By moving beyond trial-and-error development, these tools reveal training dynamics and failure modes, support more reliable design decisions, and strengthen confidence in machine-learning surrogates for engineering applications.

Petros Ellinas, Johanna Vorwerk, Spyros Chatzivasileiadis

Department of Wind and Energy Systems, Technical University of Denmark, Lyngby, Denmark

Neural Surrogate Modeling Neural Network Interpretability Adaptive Loss Weighting Neural Network Training Dynamics Power Systems

Aug 7, 2026cs.AI

FedLBW: A Loss-Based Weighting Strategy for Federated Learning on Non-IID Data in Wireless Networks

Federated Learning (FL) enables collaborative machine learning (ML) across distributed clients while preserving privacy. However, efficient model convergence in FL remains challenging, especially in wireless networks where non-independent and identically distributed (non-IID) data and frequent client dropouts are common. Traditional FL algorithms, such as FedAvg, rely solely on dataset size to weight client updates. This introduces biases towards clients with larger datasets and makes the process sensitive to non-IID data, outliers, and client dropouts. To address these challenges, we propose Federated Learning with Loss-Based Weighting (FedLBW), a novel aggregation method that assigns each client's update a weight proportional to the inverse of its validation loss, computed using a small proxy dataset on the server, rather than its dataset size. This ensures that lower-loss models exert greater influence during aggregation, prioritizing the most reliable updates and boosting overall performance. Through extensive experiments across multiple datasets, including FashionMNIST (CNN), CIFAR-10 (ResNet-18), and CIFAR-100 (ResNet-34), we demonstrate that FedLBW achieves higher accuracy and faster convergence compared to baseline algorithms such as FedAvg, FedAvgM, FedProx, FedNova, FedLAW and FedDkw, with notable improvements of up to 7.6 % higher accuracy on CIFAR-10 in extreme non-IID cases. Moreover, FedLBW showcases exceptional resilience to increasing dropout probabilities, consistently maintaining significantly higher accuracy even in challenging conditions. These results establish FedLBW as an effective and resilient solution for FL in wireless network environments, offering marked improvements in model accuracy, convergence speed, and robustness to non-IID data and client dropouts.

Majid Kundroo, Tinku Singh, Taehong Kim

aSchool of Information and Communication Engineering, Chungbuk National University, Cheongju, 28644, Republic of Korea · bSchool of Computer Science Engineering and Technology, Bennett University, Greater Noida, 201310, India

Federated Learning Aggregation Non-IID Federated Learning Adaptive Loss Weighting Federated Learning

Aug 3, 2026cs.LG

Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series Forecasting

The direction of change --- whether a series will move up or down --- is often as important as its exact value in decisiondriven applications such as risk management and financial forecasting. However, most forecasting losses optimize either point magnitude or shape and frequency structure, and none explicitly targets the direction of change. In this paper, we find that MSE-trained forecasters fail on the direction of small moves. To address this, we propose CosDir, a simple yet effective direction-aware loss that aligns the difference vectors of the prediction and the target via cosine similarity. Being scale-invariant, CosDir keeps a directional gradient on small moves, re-injecting learning signal exactly where MSE neglects it. CosDir is a lightweight, plug-in term that attaches to any backbone without architectural modification. Since the best ratio for mixing the directional and magnitude terms differs across datasets, we further propose CosDir-UW, an extension that makes this ratio adaptive by learning it during training, matching a per-dataset tuned weight with no hyperparameter. We conduct over 100K experiments, demonstrating that our method consistently and significantly improves directional accuracy while preserving magnitude accuracy, and that it outperforms various loss functions. Code is available at: https://github.com/seunghan96/cosdir.

Seunghan Lee, Jaehoon Lee, Jun Seo +9

LG AI Research

Time Series Forecasting Adaptive Loss Weighting

Aug 2, 2026cs.LG

Data-Driven Pinball-Loss Selection for Vertically Distributed Elastic-Net SVMs

The pinball-loss support vector machine is robust, but its asymmetry parameter is usually fixed in advance. We propose a data-driven elastic-net support vector machine that learns simplex-constrained weights over candidate pinball losses while retaining one classifier. The weighted loss is equivalent to a pinball loss with a data-dependent effective parameter. An empirical oracle inequality shows that, when weight regularization and simplex truncation vanish, the classifier objective at a global minimizer does not exceed that of the best fixed candidate; otherwise, the excess is explicitly bounded. For high-dimensional data, we develop a column-partitioned variable-splitting solver. It converges with a best-iterate

O(1/T)

squared-step residual rate. Under common initialization and global parameters, any column partition produces, in exact arithmetic, the same iterates and solution as centralized training. Experiments assess predictive behavior, numerical equivalence, and multi-process scalability.

Xiaofei Wu, Kai Qi, Rongmei Liang

Yunnan Key Laboratory of Statistical Modeling and Data Analysis, School of Mathematics and Statistics, Yunnan University, East Outer Ring South Road, University Town, Chenggong District, Kunming, Yunnan, China · National Center for Applied Mathematics in Chongqing, Chongqing Normal University, No. 37 University Town Middle Road, Shapingba District, Chongqing, China · Department of Statistics and Data Science, Southern University of Science and Technology, 1088 Xueyuan Avenue, Nanshan District, Shenzhen, Guangdong 518055, China

Distributed Optimization Adaptive Loss Weighting Support Vector Machines

Jul 31, 2026cs.CL

TEXAS: Task-Expert-Aware Supervision for Downstream Mixture-of-Experts LLM Adaptation

Mixture-of-Experts (MoE) language models route each token through a small subset of experts, making routing patterns useful for identifying task-relevant experts during downstream adaptation. Yet current approaches have two limitations: task experts are typically identified from aggregate routing statistics that reflect usage rather than association with successful task completion, and task-expert activations remain underexplored as signals for supervision allocation. We introduce Task-Expert-Aware Supervision (TEXAS), which combines correctness-conditioned task expert discovery with token-level supervision allocation. TEXAS compares expert activations on instances that the base model solves successfully and those it fails to solve, and retains experts more strongly activated on successful instances. During fine-tuning, it upweights answer tokens in failed instances when they activate these experts. TEXAS therefore leverages existing routing behavior without restricting adaptation to a fixed expert subset or imposing an explicit target routing distribution. Across three MoE models and six benchmarks, TEXAS achieves the best or tied-best performance in 17 of 18 settings and improves over the strongest baseline by 1.3--1.5 points on average. Ablations and further analyses validate both the discovered experts and the resulting supervision strategy.

Guanzhi Deng, Haibo Wang, Kuan Wu +5

City University of Hong Kong, Hong Kong, China · Carnegie Mellon University, Pittsburgh, USA · University of Waterloo, Ontario, Canada +1

Mixture-of-Experts Language Models Mixture of Experts LLM Fine-Tuning Adaptive Loss Weighting

Jul 28, 2026cs.CV

Beyond Static Costs: Learning-Dynamics Aware Loss Functions for Long-Tailed Classification

Deep learning models in computer vision face significant challenges when trained on long-tailed datasets, where a few majority classes dominate while many minority classes are severely underrepresented. Such imbalances frequently arise in real-world scenarios such as rare species recognition, manufacturing fault detection, and medical image understanding, leading to biased models that underperform on tail classes. Existing reweighting methods typically rely on static class frequencies to penalize the model, ignoring the dynamic nature of how effectively a network actually learns a class over time. We address this by introducing a novel Learning-Dynamics Aware Loss (LDAL) function that shifts the focus from static sample counts to dynamic learning progress. LDAL framework adjusts class weights continuously by leveraging: (i) the strength of learned feature representations (semantic scale), (ii) the intrinsic learning difficulty of each class, measured via the Shannon entropy of its predictions, and (iii) an inter-epoch regularizer term that tracks prediction shifts between consecutive epochs to stabilize training and avoid local minima. LDAL is purely a objective function which incurs negligible computational overhead while adapting to the feature learning of the model. Experimental results on multiple benchmark datasets demonstrate that our approach significantly surpasses state-of-the-art reweighting loss functions, providing an optimal trade-off between accuracy and generalizability. The source code is available at https://github.com/sdm2026/ldal

Varad Shinde, Nikhil Kumar Shrey, Magesh Rajasekaran +5

Class-Imbalanced Learning Long-Tailed Classification Adaptive Loss Weighting

Jul 23, 2026cs.LG

Context-weighted Discrete Flow Matching

Discrete flow matching provides a flexible framework for generative modeling on discrete structures. However, the standard factorized training objective exposes the model to targets of varying difficulty, mixing well-conditioned, predictable tokens with ambiguous, high-entropy ones. We empirically demonstrate that the uncertainty over the value of each token is closely related to the density of available context in its neighborhood. Motivated by this observation, we propose a simple modification to the underlying continuous-time Markov chain (CTMC) that incorporates local context information. Our context-weighted sampler improves generation quality with negligible computational overhead, while our scaled cross-entropy loss function reweights the training signal from different tokens and reduces generative perplexity by up to 63% on OpenWebText. Moreover, our approach matches a strong semi-autoregressive block diffusion baseline in quality while retaining the ability to perform generation in any order. These results highlight the role of local context as an important factor in discrete generative modeling and show that simple context-aware modifications can significantly improve both sampling and training efficiency.

Daniil Cherniavskii, Daniel Severo, Karen Ullrich

University of Amsterdam · Work done during an internship at Meta FAIR. · Meta FAIR

Non-Autoregressive Text Generation Adaptive Loss Weighting Flow-Based Generative Modeling Discrete Flow Matching

Jul 21, 2026cs.LG

KALE: Kernel Alignment with Loss Equilibration for Stable CLIP-DINOv2 Alignment at Web Scale

Kernel-based alignment of CLIP toward a vision centric teacher such as DINOv2 (KUEA) improves CLIP's visual representations while preserving text-encoder compatibility, using a fixed trade-off weight tuned on curated ImageNet-1K. We ask whether this transfers to noisy, web-scale data (CC12M) and find that it does not: the alignment term's weighted contribution falls to about 0.2% of the clean term, so under any fixed weight its gradient is effectively inert. We introduce KALE, a loss-equilibration controller that tracks both losses and adaptively rescales the alignment weight toward a target ratio, restoring the signal with no per-dataset tuning; reaching balance requires increasing the weight by roughly four orders of magnitude, and the required value is configuration-dependent, so no fixed scalar suffices. We characterize the resulting regime: a bounded high learning rate and a decaying schedule with a moderate floor are needed for stability, and the controller equilibrates rather than diverging. On a 3.3M-image CC12M subset, the aligned model preserves image-text retrieval and reproducibly improves SVHN linear probing; zero-shot improves by +2.00 over CLIP on the standard 11-dataset average, exceeding KUEA's +1.29. We report all results with explicit run-to-run variance and base our conclusions on the metrics that are stable across runs.

Michał Pawłowicz

VLM Adaptation Adaptive Loss Weighting Vision-Language Alignment

Jul 19, 2026cs.LG

Dynamic Loss Balancing for Joint SOH and RUL Prediction of Lithium-Ion Batteries via a Rotary SOH-Injected Prior Battery Transformer

The deployment of reliable lithium-ion battery management systems is crucial for accelerating electrification, yet the joint prognosis of State of Health (SOH) and Remaining Useful Life (RUL) remains severely hindered by task heteroscedasticity. Conventional multi-task learning frameworks fail to balance the bounded, low-variance noise of SOH estimation with the unbounded, nonlinearly expanding uncertainty of long-term RUL predictions. Here, we present the Rotary SOH-Injected Prior Battery Transformer (RoSIP-Batt), a unified co-estimation framework that resolves these optimization conflicts. By formulating joint prediction as a Bayesian multi-task objective, RoSIP-Batt introduces a homoscedastic uncertainty weighting mechanism to dynamically scale task-specific gradients based on learned residual noise levels. The architecture leverages decoupled dual classification tokens and a per-dimension gated fusion mechanism, secured by a gradient-detachment operator to prevent high-variance RUL updates from corrupting the stable SOH representation space. To capture electrochemical degradation patterns without relying on absolute cycle steps, Rotary Position Embedding (RoPE) is incorporated into a shared Transformer backbone to model translation-invariant relative temporal profiles. Crucially, the intermediate SOH estimate is directly injected into the RUL regression head as a physical degradation prior. Evaluations across the NASA, MIT-Stanford, and HUST datasets show that RoSIP-Batt significantly outperforms state-of-the-art baselines, reducing SOH estimation error to 1.994% MAE on NASA and restricting RUL prediction error to 62.85 cycles on Stanford. These findings establish RoSIP-Batt as a highly generalizable, computationally efficient solution suitable for real-time embedded BMS deployment.

Shuhao Chen, Tianyu Shi, Yiwen Huang +1

School of Economics and Management, Zhejiang Sci-Tech University, Hangzhou, 310018, China.

RUL Estimation Predictive Maintenance Multi-Task Learning Adaptive Loss Weighting Lithium-Ion Batteries

Jul 16, 2026cs.LG

Probabilistic Physics-Informed Neural Networks for Estimating Heterogeneous Elastic Properties from Low-Resolution and Noisy Displacement Data

Estimating spatially heterogeneous elastic properties from low-resolution displacement measurements is a severely ill-posed inverse elasticity problem because low resolution obscures spatial details needed to distinguish heterogeneous property variations, and small measurement perturbations or fitting errors are amplified through inverse estimation. Existing inverse methods often rely on high-fidelity observations and manually prespecified loss weights, limiting their adaptability and making them sensitive to noise and resolution degradation. We propose a Probabilistic Inverse Elasticity Physics-Informed Neural Network (PIE-PINN) framework for robust estimation of Young's modulus and Poisson's ratio from noisy, low-resolution displacement data. PIE-PINN models displacement observation, strain-discrepancy, and equilibrium residuals using Laplace distributions within a unified probabilistic model. To improve robustness, the framework combines a B-spline-guided displacement network with a hierarchical half-Cauchy model for displacement residual scales. The B-spline provides a smooth global representation of the displacement field, while the neural network correction captures local variations. The hierarchical scale model adaptively downweights severe displacement fitting errors, enabling more robust recovery of the latent mean displacement field. An alternating maximum-likelihood training strategy updates the mean through weighted residual minimization and updates the scales to adjust the loss weights. Systematic case studies across varying noise levels and observation resolutions demonstrate the robustness of PIE-PINN.

Tatthapong Srikitrungruang, Jaesung Lee

Wm Michael Barnes 64 Department of Industrial and Systems Engineering, Texas A&M University, College Station, TX, 77843, USA

Structural Mechanics Materials Property Prediction Adaptive Loss Weighting Physics-Informed ML PDE Inverse Problems Inverse Problems

Jul 13, 2026cs.LG

Multi-dimensional training-priority weighting based on physical information propagation paths: a unified residual-weighting framework for physics-informed neural networks

Physics-informed neural networks (PINNs) have shown promise for solving partial differential equations (PDEs); however, their synchronous optimization treats residuals of different regions and constraints equally, which is inconsistent with the progressive "from source to response" physical information propagation path, degrading training stability and accuracy. Existing causal training methods focus mainly on the temporal dimension, lacking a unified characterization of spatial and boundary dimensions. To address this, we define a unified class of training priorities according to the physical information propagation path: premise regions should be learned before dependent regions; temporal, spatial, and boundary priorities are instances of this principle. Using neural tangent kernel (NTK) dynamics, we theoretically analyze why standard PINNs do not obey this priority: their residual convergence order is governed by the NTK spectrum and is independent of the propagation path. Accordingly, we propose a unified multi-dimensional priority-constraint framework that partitions the domain along the propagation path and constructs negative-exponential residual weights, converting the physical propagation order into a training priority. For cases with coexisting priorities, we introduce a directional compatibility coefficient to clarify that "orthogonal directions can be coupled multiplicatively in synergy, whereas coaxial opposite directions cannot." Benchmark cases show that this method consistently improves the convergence behavior and prediction accuracy of PINNs on problems with clear propagation paths or constraint-dominated structures, without modifying the network architecture and with controllable additional computational cost.

Zhangyi Lian, Xinda Dong, Wenxuan Huo +3

College of Mechanical and Vehicle Engineering Chongqing University Chongqing 400030, China · State Key Laboratory of Tribology in Advanced Equipment Department of Mechanical Engineering Tsinghua University Beijing 100084, China

Neural PDE Solvers Adaptive Loss Weighting Physics-Informed ML

Jul 3, 2026cs.SD

Adaptive Loss Balancing for Multi-Task Bioacoustic Classification of Bird Species and Call Types

Reliable analysis of bird vocalisations in passive acoustic monitoring requires models handling multiple, imbalanced annotation targets. We extend BirdCallNet for joint species and call-type classification on the long-tailed WiWa dataset and investigate how task-loss balancing interacts with pretrained representations and adaptation depth. We evaluate four bird-domain encoders, ConvNeXtBS, EAT, BirdMAE, and ProtoCLR, with separate species and call-type heads under linear probing, attentive probing, and full fine-tuning. A manually tuned fixed objective is compared with homoscedastic uncertainty weighting and Dynamic Weight Averaging across all three adaptation regimes, while GradNorm is evaluated only under full fine-tuning. Results indicate that the factorised multi-task formulation yields the most consistent improvements over the combined single-task baseline for call-type recognition, while its effect on species recognition depends on the adaptation regime. Full fine-tuning is not consistently optimal: ConvNeXtBS achieves the highest mean species performance under linear probing, whereas BirdMAE provides the strongest call-type performance under attentive probing. Adaptive weighting benefits species recognition more consistently than call-type recognition. Uncertainty weighting is particularly effective for species recognition under attentive probing, whereas Dynamic Weight Averaging is generally stronger for the same task under full fine-tuning. GradNorm achieves competitive call-type performance for selected backbones but consistently underperforms other weighting strategies for species recognition and incurs higher computational and memory costs. Overall, the preferred loss-balancing strategy depends on the backbone, adaptation regime, and target task, while frozen-backbone adaptation can provide a more favourable performance-efficiency trade-off than end-to-end fine-tuning.

Paria Vali Zadeh, Sven Tomforde

Kiel University, Kiel, Germany

Class-Imbalanced Learning Multi-Task Learning Adaptive Loss Weighting Bioacoustics