# Model-Agnostic Meta Learning for Class Imbalance Adaptation

arXiv: https://arxiv.org/abs/2604.18759 · HTML: https://mlsanity.com/paper/2604.18759/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 23 of 23)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss](https://mlsanity.com/paper/1906.07413/) (2019)
- [Decoupling Representation and Classifier for Long-Tailed Recognition](https://mlsanity.com/paper/1910.09217/) (2019)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations](https://mlsanity.com/paper/1707.03237/) (2017)
- [Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference](https://mlsanity.com/paper/2412.13663/) (2024)
- [Dice Loss for Data-imbalanced NLP Tasks](https://mlsanity.com/paper/1911.02855/) (2019)
- [An Empirical Survey of Data Augmentation for Limited Data Learning in NLP](https://mlsanity.com/paper/2106.07499/) (2021)
- [Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits](https://mlsanity.com/paper/2411.18704/) (2024)
- [Deep k-NN for Noisy Labels](https://mlsanity.com/paper/2004.12289/) (2020)
- [HumAID: Human-Annotated Disaster Incidents Data from Twitter with Deep Learning Benchmarks](https://mlsanity.com/paper/2104.03090/) (2021)
- [Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts](https://mlsanity.com/paper/2210.03797/) (2022)
- [Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise](https://mlsanity.com/paper/2312.07087/) (2023)
- [Examining and Adapting Time for Multilingual Classification via Mixture of Temporal Experts](https://mlsanity.com/paper/2502.08825/) (2025)
- [MultiConIR: Towards multi-condition Information Retrieval](https://mlsanity.com/paper/2503.08046/) (2025)
- [Cultivating Multidisciplinary AI Workforce Development on iTiger GPU Cluster: Practices and Challenges](https://mlsanity.com/paper/2504.14786/) (2025)
- [Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models](https://mlsanity.com/paper/2507.18504/) (2025)
- [Improving Generalization via Meta-Learning on Hard Samples](https://mlsanity.com/paper/2403.12236/) (2024)
- [Learning to Select Pivotal Samples for Meta Re-weighting](https://mlsanity.com/paper/2302.04418/) (2023)
- [Learning from Noisy Labels via Self-Taught On-the-Fly Meta Loss Rescaling](https://mlsanity.com/paper/2412.12955/) (2024)

## Built on by (most cited first, 1 of 1)

- [AIA2: Attribute-Agnostic Imbalance Augmentation for Subgroup Robustness](https://mlsanity.com/paper/2608.30297/) (2026)

## Abstract (arXiv)

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.