Model-Agnostic Meta Learning for Class Imbalance Adaptation

• URL: http://arxiv.org/abs/2604.18759v1
• Date: Mon, 20 Apr 2026 19:07:56 GMT
• Title: Model-Agnostic Meta Learning for Class Imbalance Adaptation
• Abstract summary: Class imbalance is a widespread challenge in NLP tasks, hindering robust performance across diverse domains and applications.<n>We introduce Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses both class imbalance and data difficulty.
• Score: 3.2488051786523813
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class imbalance is a widespread challenge in NLP tasks, significantly hindering robust performance across diverse domains and applications. We introduce Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses both class imbalance and data difficulty. HAMR employs bi-level optimizations to dynamically estimate instance-level weights that prioritize genuinely challenging samples and minority classes, while a neighborhood-aware resampling mechanism amplifies training focus on hard examples and their semantically similar neighbors. We validate HAMR on six imbalanced datasets covering multiple tasks and spanning biomedical, disaster response, and sentiment domains. Experimental results show that HAMR achieves substantial improvements for minority classes and consistently outperforms strong baselines. Extensive ablation studies demonstrate that our proposed modules synergistically contribute to performance gains and highlight HAMR as a flexible and generalizable approach for class imbalance adaptation. Code is available at https://github.com/trust-nlp/ImbalanceLearning.

Related papers

• SAW: Stage-Aware Dynamic Weighting for Multi-Objective Reinforcement Learning in Large Language Models [66.92079232778707]
  We propose Stage-Aware Dynamic Weighting (SAW) as a lightweight, algorithm-agnostic dynamic weighting mechanism.<n>SAW reweights each dimension's reward or advantage contribution by its relative informativeness within the batch.<n> Experiments on tool-calling and text summarization tasks demonstrate that SAW consistently improves both training efficiency and final performance.
  arXiv  Detail & Related papers  (2026-06-05T10:00:19Z)
• Label What Matters: Modality-Balanced and Difficulty-Aware Multimodal Active Learning [13.136629024689432]
  We propose RL-MBA, a reinforcement-learning framework for modality-balanced, difficulty-aware active learning.<n>Experiments on Food101, KineticsSound, and VGGSound demonstrate that RL-MBA consistently outperforms strong baselines.
  arXiv  Detail & Related papers  (2026-03-26T07:26:48Z)
• BALM: A Model-Agnostic Framework for Balanced Multimodal Learning under Imbalanced Missing Rates [1.9650181409005112]
  BALM is a model-agnostic plug-in framework to achieve balanced multimodal learning under IMR.<n>We show that BALM consistently enhances robustness and improves performance under diverse missing and imbalance settings.
  arXiv  Detail & Related papers  (2026-03-20T07:47:09Z)
• Dual-granularity Sinkhorn Distillation for Enhanced Learning from Long-tailed Noisy Data [67.25796812343454]
  Real-world datasets for deep learning frequently suffer from the co-occurring challenges of class imbalance and label noise.<n>We propose Dual-granularity Sinkhorn Distillation (D-SINK), a novel framework that enhances dual robustness by distilling and integrating complementary insights.<n>Experiments on benchmark datasets demonstrate that D-SINK significantly improves robustness and achieves strong empirical performance in learning from long-tailed noisy data.
  arXiv  Detail & Related papers  (2025-10-09T13:05:27Z)
• LSH-DynED: A Dynamic Ensemble Framework with LSH-Based Undersampling for Evolving Multi-Class Imbalanced Classification [3.360922672565235]
  This study introduces a novel, robust, and resilient approach to address these challenges.<n>It integrates Locality Sensitive Hashing with Random Hyperplane Projections (LSH-RHP) into the Dynamic Ensemble Diversification (DynED) framework.<n>We conduct comprehensive experiments on 23 real-world and ten semi-synthetic datasets and compare LSH-DynED with 15 state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-06-24T22:46:47Z)
• Rethinking Multimodal Learning from the Perspective of Mitigating Classification Ability Disproportion [6.749782429802639]
  Multimodal learning is significantly constrained by modality imbalance.<n>We propose a novel approach to balance the classification ability of weak and strong modalities by incorporating the principle of boosting.
  arXiv  Detail & Related papers  (2025-02-27T14:12:20Z)
• Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining [55.262510814326035]
  Existing reweighting strategies primarily focus on group-level data importance.<n>We introduce novel algorithms for dynamic, instance-level data reweighting.<n>Our framework allows us to devise reweighting strategies deprioritizing redundant or uninformative data.
  arXiv  Detail & Related papers  (2025-02-10T17:57:15Z)
• SeMi: When Imbalanced Semi-Supervised Learning Meets Mining Hard Examples [54.760757107700755]
  Semi-Supervised Learning (SSL) can leverage abundant unlabeled data to boost model performance.<n>The class-imbalanced data distribution in real-world scenarios poses great challenges to SSL, resulting in performance degradation.<n>We propose a method that enhances the performance of Imbalanced Semi-Supervised Learning by Mining Hard Examples (SeMi)
  arXiv  Detail & Related papers  (2025-01-10T14:35:16Z)
• On-the-fly Modulation for Balanced Multimodal Learning [53.616094855778954]
  Multimodal learning is expected to boost model performance by integrating information from different modalities. The widely-used joint training strategy leads to imbalanced and under-optimized uni-modal representations. We propose On-the-fly Prediction Modulation (OPM) and On-the-fly Gradient Modulation (OGM) strategies to modulate the optimization of each modality.
  arXiv  Detail & Related papers  (2024-10-15T13:15:50Z)
• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Tackling Diverse Minorities in Imbalanced Classification [80.78227787608714]
  Imbalanced datasets are commonly observed in various real-world applications, presenting significant challenges in training classifiers. We propose generating synthetic samples iteratively by mixing data samples from both minority and majority classes. We demonstrate the effectiveness of our proposed framework through extensive experiments conducted on seven publicly available benchmark datasets.
  arXiv  Detail & Related papers  (2023-08-28T18:48:34Z)
• Online Learning With Adaptive Rebalancing in Nonstationary Environments [11.501721946030779]
  We provide new insights into learning from nonstationary and imbalanced data in online learning. We propose the novel Adaptive REBAlancing (AREBA) algorithm that selectively includes in the training set a subset of the majority and minority examples.
  arXiv  Detail & Related papers  (2020-09-24T20:40:04Z)

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.