Class-Specific Branch Attention for Mitigating Gradient Interference under Class Imbalance

• URL: http://arxiv.org/abs/2606.05740v1
• Date: Thu, 04 Jun 2026 06:07:08 GMT
• Title: Class-Specific Branch Attention for Mitigating Gradient Interference under Class Imbalance
• Abstract summary: We identify a complementary optimization-level pathology: inter-class gradient interference within shared representations.<n>We propose a lightweight modification, Class-Specific Branch Attention (CSBA), that enables branch-specific channel reweighting to reduce gradient coupling.<n> Empirically, CSBA improves minority-class performance, increasing the F1 score for the Physical-Damage class from 0.261 to 0.522 under severe imbalance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks trained under severe class imbalance often exhibit degraded performance, typically attributed to statistical bias. In this work, we identify a complementary optimization-level pathology: inter-class gradient interference within shared representations, where gradients from majority classes suppress minority-class learning. To analyze this phenomenon, we introduce a diagnostic framework based on layer-wise gradient flow analysis and a Gradient Conflict Matrix, which quantifies interference using cosine similarity between class-specific gradients. Using this framework, we study multi-branch convolutional architectures and propose a lightweight modification, Class-Specific Branch Attention (CSBA), that enables branch-specific channel reweighting to reduce gradient coupling. This mechanism promotes implicit feature decoupling across branches while preserving architectural simplicity. Empirically, CSBA improves minority-class performance, increasing the F1 score for the Physical-Damage class from 0.261 to 0.522 under severe imbalance, while maintaining comparable overall accuracy. Validation on CIFAR-10-LT confirms that this behavior generalizes across imbalanced visual recognition settings, with Macro-F1 improving from 0.595 to 0.655. More broadly, our findings highlight the importance of considering optimization dynamics alongside statistical methods when designing architectures for imbalanced learning.

Related papers

• Mitigating The Effect of Class Imbalance in Data with Hierarchical and Dependable Structure [0.0]
  Classifying cybersecurity vulnerabilities using the Common Weaknession (CWE) taxonomy is challenging.<n>Oversampling techniques are widely adopted to mitigate class imbalance, but their effectiveness for hierarchical CWE text classification remains largely unexplored.<n>This paper proposes a hierarchy-aware RoBERTa framework that explicitly incorporates CWE structural information through learnable parent-class embeddings.
  arXiv  Detail & Related papers  (2026-07-13T15:58:11Z)
• PulmoSight-XAI: An Explainable Multi-View Attention Ensemble with Gradient Boosting Meta-Learning for Multi-Label Chest X-Ray Classification [1.2744523252873352]
  We propose an explainable hierarchical multi-view ensemble framework for the robust classification of 14 thoracic pathologies.<n>The framework employs view-specific training by independently modeling frontal and lateral radiographs.<n>The framework achieves state-of-the-art macro-average AUROC scores of 0.9319 for frontal and 0.9154 for lateral radiographs.
  arXiv  Detail & Related papers  (2026-07-05T19:50:53Z)
• SimReg: Achieving Higher Performance in the Pretraining via Embedding Similarity Regularization [55.63565289584336]
  SimReg is an embedding similarity regularization loss that explicitly encourages token representations with the same ground-truth label within each sequence to be more similar.<n>Our analysis reveals that this mechanism introduces gains by enlarging multi-classification margins, thereby enabling more efficient classification.
  arXiv  Detail & Related papers  (2026-05-09T08:59:13Z)
• Beyond the Markovian Assumption: Robust Optimization via Fractional Weyl Integrals in Imbalanced Data [0.0]
  We introduce a novel optimization algorithm grounded in Fractional Calculus.<n>By isolating the core memory engine of the generalized fractional derivative, we replace the instantaneous gradient with a dynamically weighted historical sequence.<n> Empirical evaluations demonstrate that our method prevents overfitting in medical diagnostics and achieves an approximately 40 percent improvement in PRAUC over classicals.
  arXiv  Detail & Related papers  (2026-03-09T13:38:45Z)
• Advancing Analytic Class-Incremental Learning through Vision-Language Calibration [6.871141687303144]
  Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability.<n>We propose textbfVILA, a novel dual-branch framework that advances analytic CIL via a two-level vision-language calibration strategy.<n>Our framework harmonizes high-fidelity prediction with the simplicity of analytic learning.
  arXiv  Detail & Related papers  (2026-02-14T08:32:51Z)
• Reducing Class-Wise Performance Disparity via Margin Regularization [82.81746960548382]
  Deep neural networks often exhibit substantial disparities in class-wise accuracy, even when trained on class-balanced data.<n>We present Margin Regularization for Performance Disparity Reduction (MR$2$), a theoretically principled regularization for classification.<n>Our analysis reveals how per-class feature variability contributes to error, motivating the use of larger margins for hard classes.
  arXiv  Detail & Related papers  (2026-01-30T12:56:08Z)
• Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization [63.169050703903515]
  We propose Aes-R1, a comprehensive aesthetic reasoning framework with reinforcement learning (RL)<n>Aes-R1 integrates a pipeline, AesCoT, to construct and filter high-quality chain-of-thought aesthetic reasoning data.<n>Experiments demonstrate that Aes-R1 improves the backbone's average PLCC/SRCC by 47.9%/34.8%.
  arXiv  Detail & Related papers  (2025-09-26T04:55:00Z)
• Adaptive Federated Learning Over the Air [108.62635460744109]
  We propose a federated version of adaptive gradient methods, particularly AdaGrad and Adam, within the framework of over-the-air model training. Our analysis shows that the AdaGrad-based training algorithm converges to a stationary point at the rate of $mathcalO( ln(T) / T 1 - frac1alpha ).
  arXiv  Detail & Related papers  (2024-03-11T09:10:37Z)
• Balanced Classification: A Unified Framework for Long-Tailed Object Detection [74.94216414011326]
  Conventional detectors suffer from performance degradation when dealing with long-tailed data due to a classification bias towards the majority head categories. We introduce a unified framework called BAlanced CLassification (BACL), which enables adaptive rectification of inequalities caused by disparities in category distribution. BACL consistently achieves performance improvements across various datasets with different backbones and architectures.
  arXiv  Detail & Related papers  (2023-08-04T09:11:07Z)
• Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection [37.99031842449251]
  Video anomaly detection under weak supervision presents significant challenges. We present a weakly supervised anomaly detection framework that focuses on efficient context modeling and enhanced semantic discriminability. Our approach significantly improves the detection accuracy of certain anomaly sub-classes, underscoring its practical value and efficacy.
  arXiv  Detail & Related papers  (2023-06-26T06:45:16Z)
• A Theoretical Analysis of the Learning Dynamics under Class Imbalance [0.10231119246773925]
  We show that the learning curves for minority and majority classes follow sub-optimal trajectories when training with a gradient-based trajectory. This slowdown is related to the imbalance ratio and can be traced back to a competition between the optimization of different classes. We find that GD is not guaranteed to decrease the loss for each class but that this problem can be addressed by performing a per-class normalization of the gradient.
  arXiv  Detail & Related papers  (2022-07-01T12:54:38Z)
• Learning with Multiclass AUC: Theory and Algorithms [141.63211412386283]
  Area under the ROC curve (AUC) is a well-known ranking metric for problems such as imbalanced learning and recommender systems. In this paper, we start an early trial to consider the problem of learning multiclass scoring functions via optimizing multiclass AUC metrics.
  arXiv  Detail & Related papers  (2021-07-28T05:18:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.