---
title: "Model-Agnostic Meta Learning for Class Imbalance Adaptation"
description: "To address this, they propose Hardness-Aware Meta-Resample (HAMR), which combines two components: Learned… 44 references."
authors: ["Hanshu Rao", "Guangzeng Han", "Xiaolei Huang"]
year: 2026
venue: "Findings of the Association for Computational Linguistics: ACL 2026"
source: "https://aclanthology.org/2026.findings-acl.507/"
doi: "10.18653/v1/2026.findings-acl.507"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/rao-2026-model-agnostic-meta-learning-class/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/rao-2026-model-agnostic-meta-learning-class/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/) / Model-Agnostic Meta Learning for Class Imbalance Adaptation

# Model-Agnostic Meta Learning for Class Imbalance Adaptation

**Authors:** Hanshu Rao, [Guangzeng Han](https://md.research.elamur.ai/free/en/authors/guangzeng-han/) and [Xiaolei Huang](https://md.research.elamur.ai/free/en/authors/xiaolei-huang/) · **Year:** 2026 · **Venue:** [Findings of the Association for Computational Linguistics: ACL 2026](https://md.research.elamur.ai/free/en/venues/findings/) ([Findings of the Association for Computational Linguistics 2026](https://md.research.elamur.ai/free/en/venues/findings/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.findings-acl.507/) · [PDF](https://aclanthology.org/2026.findings-acl.507.pdf) · [DOI 10.18653/v1/2026.findings-acl.507](https://doi.org/10.18653/v1/2026.findings-acl.507) · [OpenAlex](https://openalex.org/W7166828501)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Skewed label distributions hurt NLP models: they learn to favor frequent classes and overlook rare ones that often matter most. The authors argue that common remedies, such as class-frequency reweighting, focal or Dice loss, and oversampling, use fixed rules and treat every example in a class the same. In practice, difficulty varies within a class. To address this, they propose Hardness-Aware Meta-Resample (HAMR), which combines two components:

- **Learned per-instance weights.** A small weighting network turns normalized per-example losses into weights. It is trained through bi-level meta-optimization against a class-balanced meta-validation set.
- **Neighborhood-based resampling.** Sampling is shifted toward hard examples and their nearest semantic neighbors in embedding space.

HAMR is evaluated on six imbalanced NER and text classification benchmarks from the biomedical, disaster response and sentiment domains. It beats strong baselines consistently, and the gains grow as the imbalance becomes more extreme. Rare classes improve without any loss on frequent ones, and ablations show that both modules contribute. The framework is model-agnostic, which makes it relevant for low-resource or long-tailed labeling settings.

## Key points
- **Weighting module.** Difficulty is measured as the maximum token loss per sentence for NER and as per-example cross-entropy for classification. Scores are z-normalized within each batch, and the resulting weights are rescaled to a mean of 1 and clipped.
- **Meta-optimization loop.** The model first takes a trial update using pre-meta weights. The weighting network is then updated from the loss on a balanced meta-set, built by topping up classes to the median validation-class count. Finally, recomputed post-meta weights drive the real update.
- **Resampling module.** The hardest ~20% of samples are identified using EMA-smoothed weights. Their k nearest neighbors are retrieved with KNN over a FAISS index, and these neighbors receive a boost score. The sampling probability combines temperature-smoothed hardness with this boost.
- **Results.** Quartile analysis shows clear gains on infrequent classes. HAMR transfers across architectures and scales, with the strongest benefits on encoder backbones for structured prediction.
- **Limitations and code.** HAMR adds compute cost, depends on embedding quality, and has only been tested on classification and NER. Code is available at github.com/trust-nlp/ImbalanceLearning.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Memphis](https://md.research.elamur.ai/free/en/universities/university-of-memphis/) — University, Memphis, United States · 4 works · 325 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

## Cite

Cite as: Hanshu Rao, Guangzeng Han and Xiaolei Huang. 2026. Model-Agnostic Meta Learning for Class Imbalance Adaptation. Findings of the Association for Computational Linguistics: ACL 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{rao2026model,
  title = {{Model-Agnostic Meta Learning for Class Imbalance Adaptation}},
  author = {Hanshu Rao, Guangzeng Han and Xiaolei Huang},
  booktitle = {Findings of the Association for Computational Linguistics: ACL 2026},
  year = {2026},
  doi = {10.18653/v1/2026.findings-acl.507},
  url = {https://doi.org/10.18653/v1/2026.findings-acl.507}
}
```

- [← previous Model Directions, Not Words: Mechanistic Topic Models Using Sparse Autoencoders](https://md.research.elamur.ai/free/en/papers/zheng-2026-model-directions-not-words-mechanistic/)
- [next → Model-Based Imaginative Planning for Embodied Agents](https://md.research.elamur.ai/free/en/papers/song-2026-model-based-imaginative-planning-embodied/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/37/)

## References

44 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Firoj Alam, Umair Qazi, Muhammad Imran, and Ferda Ofli. 2021. Humaid: Human-annotated disaster incidents data from twitter with deep learning benchmarks. In Proceedings of the International AAAI Conference on Web and Social Media, volume 15, pages 933–942. [find](https://scholar.google.com/scholar?q=Firoj+Alam%2C+Umair+Qazi%2C+Muhammad+Imran%2C+and+Ferda+Ofli%2E+2021%2E+Humaid%3A+Human%2Dannotated+disaster+incidents+data+from+twitter+with+deep+learning+benchmarks%2E+In+Proceedings+of+the+International+AAAI+Confe)
2. Naif Radi Aljohani, Ayman Fayoumi, and Saeed-Ul Hassan. 2023. A novel focal-loss and class-weight-aware convolutional neural network for the classification of in-text citations. Journal of Information Science, 49(1):79–92. [find](https://scholar.google.com/scholar?q=Naif+Radi+Aljohani%2C+Ayman+Fayoumi%2C+and+Saeed%2DUl+Hassan%2E+2023%2E+A+novel+focal%2Dloss+and+class%2Dweight%2Daware+convolutional+neural+network+for+the+classification+of+in%2Dtext+citations%2E+Journal+of+Information)
3. Dara Bahri, Heinrich Jiang, and Maya Gupta. 2020. Deep k-NN for noisy labels. In Proceedings of the 37th International Conference on Machine Learning, volume 119 of Proceedings of Machine Learning Research, pages 540–550. PMLR. [find](https://scholar.google.com/scholar?q=Dara+Bahri%2C+Heinrich+Jiang%2C+and+Maya+Gupta%2E+2020%2E+Deep+k%2DNN+for+noisy+labels%2E+In+Proceedings+of+the+37th+International+Conference+on+Machine+Learning%2C+volume+119+of+Proceedings+of+Machine+Learning+Res)
4. Kevin W. Bowyer, Nitesh V. Chawla, Lawrence O. Hall, and W. Philip Kegelmeyer. 2011. SMOTE: synthetic minority over-sampling technique. CoRR, abs/1106.1813. — [arXiv:1106.1813](https://arxiv.org/abs/1106.1813) [find](https://scholar.google.com/scholar?q=Kevin+W%2E+Bowyer%2C+Nitesh+V%2E+Chawla%2C+Lawrence+O%2E+Hall%2C+and+W%2E+Philip+Kegelmeyer%2E+2011%2E+SMOTE%3A+synthetic+minority+over%2Dsampling+technique%2E+CoRR%2C+abs%2F1106%2E1813%2E+%E2%80%94+%5BarXiv%3A1106%2E1813%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F1)
5. Kaidi Cao, Colin Wei, Adrien Gaidon, Nikos Arechiga, and Tengyu Ma. 2019. Learning imbalanced datasets with label-distribution-aware margin loss. Advances in neural information processing systems, 32. [find](https://scholar.google.com/scholar?q=Kaidi+Cao%2C+Colin+Wei%2C+Adrien+Gaidon%2C+Nikos+Arechiga%2C+and+Tengyu+Ma%2E+2019%2E+Learning+imbalanced+datasets+with+label%2Ddistribution%2Daware+margin+loss%2E+Advances+in+neural+information+processing+systems%2C+32%2E)
6. Jiaao Chen, Derek Tam, Colin Raffel, Mohit Bansal, and Diyi Yang. 2023. [An empirical survey of data augmentation for limited data learning in nlp](https://md.research.elamur.ai/free/en/papers/chen-2023-empirical-survey-data-augmentation-limited/). Transactions of the Association for Computational Linguistics, 11:191–211.
7. Nigel Collier and Jin-Dong Kim. 2004. [Introduction to the bio-entity recognition task at JNLPBA](https://md.research.elamur.ai/free/en/papers/collier-2004-introduction-bio-entity-recognition-task/). In Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications (NLPBA/BioNLP), pages 73–78, Geneva, Switzerland. COLING.
8. Aaron Grattafiori, Abhimanyu Dubey, Abhinav Jauhri, Abhinav Pandey, Abhishek Kadian, Ahmad Al-Dahle, Aiesha Letman, Akhil Mathur, Alan Schelten, Alex Vaughan, and 1 others. 2024. [The llama 3 herd of models](https://md.research.elamur.ai/free/en/papers/grattafiori-2024-llama-3-herd-models/). Technical report, Meta Research. ArXiv preprint arXiv:2407.21783.
9. Guangzeng Han, Weisi Liu, and Xiaolei Huang. 2025. Attributes as textual genes: Leveraging LLMs as genetic algorithm simulators for conditional synthetic data generation. In Findings of the Association for Computational Linguistics: EMNLP 2025, pages 19367–19389, Suzhou, China. Association for Compu… [find](https://scholar.google.com/scholar?q=Guangzeng+Han%2C+Weisi+Liu%2C+and+Xiaolei+Huang%2E+2025%2E+Attributes+as+textual+genes%3A+Leveraging+LLMs+as+genetic+algorithm+simulators+for+conditional+synthetic+data+generation%2E+In+Findings+of+the+Associatio)
10. Haibo He and Edwardo A. Garcia. 2009. Learning from imbalanced data. IEEE Transactions on Knowledge and Data Engineering, 21(9):1263–1284. [find](https://scholar.google.com/scholar?q=Haibo+He+and+Edwardo+A%2E+Garcia%2E+2009%2E+Learning+from+imbalanced+data%2E+IEEE+Transactions+on+Knowledge+and+Data+Engineering%2C+21%289%29%3A1263%E2%80%931284%2E)
11. Pengcheng He, Jianfeng Gao, and Weizhu Chen. 2021. [Debertav3: Improving deberta using electra-style pre-training with gradient-disentangled embedding sharing](https://md.research.elamur.ai/free/en/papers/he-2021-debertav3-improving-deberta-using-electra/). Preprint, arXiv:2111.09543.
12. Michael Heck, Christian Geishauser, Nurul Lubis, Carel van Niekerk, Shutong Feng, Hsien-Chin Lin, Benjamin Matthias Ruppik, Renato Vukovic, and Milica Gašić. 2024. Learning from noisy labels via self-taught on-the-fly meta loss rescaling. Preprint, arXiv:2412.12955. — [arXiv:2412.12955](https://arxiv.org/abs/2412.12955) [find](https://scholar.google.com/scholar?q=Michael+Heck%2C+Christian+Geishauser%2C+Nurul+Lubis%2C+Carel+van+Niekerk%2C+Shutong+Feng%2C+Hsien%2DChin+Lin%2C+Benjamin+Matthias+Ruppik%2C+Renato+Vukovic%2C+and+Milica+Ga%C5%A1ic%CC%81%2E+2024%2E+Learning+from+noisy+labels+via+self)
13. Sophie Henning, William Beluch, Alexander Fraser, and Annemarie Friedrich. 2023. A survey of methods for addressing class imbalance in deep-learning based natural language processing. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, page… [find](https://scholar.google.com/scholar?q=Sophie+Henning%2C+William+Beluch%2C+Alexander+Fraser%2C+and+Annemarie+Friedrich%2E+2023%2E+A+survey+of+methods+for+addressing+class+imbalance+in+deep%2Dlearning+based+natural+language+processing%2E+In+Proceedings+o)
14. Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, and Weizhu Chen. 2021. [Lora: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). CoRR, abs/2106.09685.
15. Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang Song, and Serge Belongie. 2019. Class-balanced loss based on effective number of samples. Preprint, arXiv:1901.05555. [find](https://scholar.google.com/scholar?q=Yin+Cui%2C+Menglin+Jia%2C+Tsung%2DYi+Lin%2C+Yang+Song%2C+and+Serge+Belongie%2E+2019%2E+Class%2Dbalanced+loss+based+on+effective+number+of+samples%2E+Preprint%2C+arXiv%3A1901%2E05555%2E)
16. Guangzheng Hu, Feng Liu, Mingming Gong, Guanghui Wang, and Liuhua Peng. 2025. Learning imbalanced data with beneficial label noise. In Forty-second International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Guangzheng+Hu%2C+Feng+Liu%2C+Mingming+Gong%2C+Guanghui+Wang%2C+and+Liuhua+Peng%2E+2025%2E+Learning+imbalanced+data+with+beneficial+label+noise%2E+In+Forty%2Dsecond+International+Conference+on+Machine+Learning%2E)
17. Matthijs Douze, Alexandr Guzhva, Chengqi Deng, Jeff Johnson, Gergely Szilvasy, Pierre-Emmanuel Mazaré, Maria Lomeli, Lucas Hosseini, and Hervé Jégou. 2025. [The faiss library](https://md.research.elamur.ai/free/en/papers/douze-2024-faiss-library/). IEEE Transactions on Big Data, pages 1–17.
18. Nishant Jain, Arun S. Suggala, and Pradeep Shenoy. 2024. Improving generalization via meta-learning on hard samples. In 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 27590–27599. [find](https://scholar.google.com/scholar?q=Nishant+Jain%2C+Arun+S%2E+Suggala%2C+and+Pradeep+Shenoy%2E+2024%2E+Improving+generalization+via+meta%2Dlearning+on+hard+samples%2E+In+2024+IEEE%2FCVF+Conference+on+Computer+Vision+and+Pattern+Recognition+%28CVPR%29%2C+page)
19. Sergey Edunov, Myle Ott, Michael Auli, and David Grangier. 2018. Understanding back-translation at scale. arXiv preprint arXiv:1808.09381. [find](https://scholar.google.com/scholar?q=Sergey+Edunov%2C+Myle+Ott%2C+Michael+Auli%2C+and+David+Grangier%2E+2018%2E+Understanding+back%2Dtranslation+at+scale%2E+arXiv+preprint+arXiv%3A1808%2E09381%2E)
20. Justin M Johnson and Taghi M Khoshgoftaar. 2019. Survey on deep learning with class imbalance. Journal of big data, 6(1):1–54. [find](https://scholar.google.com/scholar?q=Justin+M+Johnson+and+Taghi+M+Khoshgoftaar%2E+2019%2E+Survey+on+deep+learning+with+class+imbalance%2E+Journal+of+big+data%2C+6%281%29%3A1%E2%80%9354%2E)
21. Chelsea Finn, Pieter Abbeel, and Sergey Levine. 2017. [Model-agnostic meta-learning for fast adaptation of deep networks](https://md.research.elamur.ai/free/en/papers/finn-2017-model-agnostic-meta-learning-fast/). In Proceedings of the 34th International Conference on Machine Learning - Volume 70, ICML’17, page 1126–1135. JMLR.org.
22. Bingyi Kang, Saining Xie, Marcus Rohrbach, Zhicheng Yan, Albert Gordo, Jiashi Feng, and Yannis Kalantidis. 2020. Decoupling representation and classifier for long-tailed recognition. Preprint, arXiv:1910.09217. [find](https://scholar.google.com/scholar?q=Bingyi+Kang%2C+Saining+Xie%2C+Marcus+Rohrbach%2C+Zhicheng+Yan%2C+Albert+Gordo%2C+Jiashi+Feng%2C+and+Yannis+Kalantidis%2E+2020%2E+Decoupling+representation+and+classifier+for+long%2Dtailed+recognition%2E+Preprint%2C+arXiv%3A1)
23. Xiaoya Li, Xiaofei Sun, Yuxian Meng, Junjun Liang, Fei Wu, and Jiwei Li. 2020. [Dice loss for data-imbalanced NLP tasks](https://md.research.elamur.ai/free/en/papers/li-2020-dice-loss-data-imbalanced-nlp/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 465–476, Online. Association for Computational Linguistics.
24. Tsung-Yi Lin, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2020. Focal loss for dense object detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(2):318–327. [find](https://scholar.google.com/scholar?q=Tsung%2DYi+Lin%2C+Priya+Goyal%2C+Ross+Girshick%2C+Kaiming+He%2C+and+Piotr+Doll%C3%A1r%2E+2020%2E+Focal+loss+for+dense+object+detection%2E+IEEE+Transactions+on+Pattern+Analysis+and+Machine+Intelligence%2C+42%282%29%3A318%E2%80%93327%2E)
25. Jingjing Liu, Panupong Pasupat, Scott Cyphers, and Jim Glass. 2013. Asgard: A portable architecture for multilingual dialogue systems. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 8386–8390. [find](https://scholar.google.com/scholar?q=Jingjing+Liu%2C+Panupong+Pasupat%2C+Scott+Cyphers%2C+and+Jim+Glass%2E+2013%2E+Asgard%3A+A+portable+architecture+for+multilingual+dialogue+systems%2E+In+Proc%2E+IEEE+International+Conference+on+Acoustics%2C+Speech+and+S)
26. Pei Liu, Xuemin Wang, Chao Xiang, and Weiye Meng. 2020. A survey of text data augmentation. In 2020 International Conference on Computer Communication and Network Security (CCNS), pages 191–195. IEEE. [find](https://scholar.google.com/scholar?q=Pei+Liu%2C+Xuemin+Wang%2C+Chao+Xiang%2C+and+Weiye+Meng%2E+2020%2E+A+survey+of+text+data+augmentation%2E+In+2020+International+Conference+on+Computer+Communication+and+Network+Security+%28CCNS%29%2C+pages+191%E2%80%93195%2E+IEEE%2E)
27. Weisi Liu, Guangzeng Han, and Xiaolei Huang. 2025. Examining and adapting time for multilingual classification via mixture of temporal experts. In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (… [find](https://scholar.google.com/scholar?q=Weisi+Liu%2C+Guangzeng+Han%2C+and+Xiaolei+Huang%2E+2025%2E+Examining+and+adapting+time+for+multilingual+classification+via+mixture+of+temporal+experts%2E+In+Proceedings+of+the+2025+Conference+of+the+Nations+of+)
28. Xuan Lu, Sifan Liu, Bochao Yin, Yongqi Li, Xinghao Chen, Hui Su, Yaohui Jin, Wenjun Zeng, and Xiaoyu Shen. 2025. Multiconir: Towards multi-condition information retrieval. Preprint. [find](https://scholar.google.com/scholar?q=Xuan+Lu%2C+Sifan+Liu%2C+Bochao+Yin%2C+Yongqi+Li%2C+Xinghao+Chen%2C+Hui+Su%2C+Yaohui+Jin%2C+Wenjun+Zeng%2C+and+Xiaoyu+Shen%2E+2025%2E+Multiconir%3A+Towards+multi%2Dcondition+information+retrieval%2E+Preprint%2E)
29. Vinicius Eiji Martins, Alberto Cano, and Sylvio Barbon Junior. 2023. Meta-learning for dynamic tuning of active learning on stream classification. Pattern Recognition, 138:109359. [find](https://scholar.google.com/scholar?q=Vinicius+Eiji+Martins%2C+Alberto+Cano%2C+and+Sylvio+Barbon+Junior%2E+2023%2E+Meta%2Dlearning+for+dynamic+tuning+of+active+learning+on+stream+classification%2E+Pattern+Recognition%2C+138%3A109359%2E)
30. Daniel Morales-Brotons, Thijs Vogels, and Hadrien Hendrikx. 2024. Exponential moving average of weights in deep learning: Dynamics and benefits. Transactions on Machine Learning Research. [find](https://scholar.google.com/scholar?q=Daniel+Morales%2DBrotons%2C+Thijs+Vogels%2C+and+Hadrien+Hendrikx%2E+2024%2E+Exponential+moving+average+of+weights+in+deep+learning%3A+Dynamics+and+benefits%2E+Transactions+on+Machine+Learning+Research%2E)
31. Alejandro Moreo, Andrea Esuli, and Fabrizio Sebastiani. 2016. Distributional random oversampling for imbalanced text classification. In Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR ’16, page 805–808, New York, NY, USA. Associa… [find](https://scholar.google.com/scholar?q=Alejandro+Moreo%2C+Andrea+Esuli%2C+and+Fabrizio+Sebastiani%2E+2016%2E+Distributional+random+oversampling+for+imbalanced+text+classification%2E+In+Proceedings+of+the+39th+International+ACM+SIGIR+Conference+on+Re)
32. Sota Nemoto, Shunsuke Kitada, and Hitoshi Iyatomi. 2024. Majority or minority: Data imbalance learning method for named entity recognition. IEEE Access. [find](https://scholar.google.com/scholar?q=Sota+Nemoto%2C+Shunsuke+Kitada%2C+and+Hitoshi+Iyatomi%2E+2024%2E+Majority+or+minority%3A+Data+imbalance+learning+method+for+named+entity+recognition%2E+IEEE+Access%2E)
33. Cristian Padurariu and Mihaela Elena Breaban. 2019. Dealing with data imbalance in text classification. Procedia Computer Science, 159:736–745. [find](https://scholar.google.com/scholar?q=Cristian+Padurariu+and+Mihaela+Elena+Breaban%2E+2019%2E+Dealing+with+data+imbalance+in+text+classification%2E+Procedia+Computer+Science%2C+159%3A736%E2%80%93745%2E)
34. Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, and 1 others. 2019. [Pytorch: An imperative style, high-performance deep learning library](https://md.research.elamur.ai/free/en/papers/paszke-2019-pytorch-imperative-style-high-performance/). Advances in neural information processing systems, 32.
35. Mengye Ren, Wenyuan Zeng, Binh Yang, and Raquel Urtasun. 2018. Learning to reweight examples for robust deep learning. In International Conference on Machine Learning. [find](https://scholar.google.com/scholar?q=Mengye+Ren%2C+Wenyuan+Zeng%2C+Binh+Yang%2C+and+Raquel+Urtasun%2E+2018%2E+Learning+to+reweight+examples+for+robust+deep+learning%2E+In+International+Conference+on+Machine+Learning%2E)
36. Mayira Sharif, Guangzeng Han, Weisi Liu, and Xiaolei Huang. 2025. Cultivating multidisciplinary research and education on gpu infrastructure for mid-south institutions at the university of memphis: Practice and challenge. Preprint, arXiv:2504.14786. [find](https://scholar.google.com/scholar?q=Mayira+Sharif%2C+Guangzeng+Han%2C+Weisi+Liu%2C+and+Xiaolei+Huang%2E+2025%2E+Cultivating+multidisciplinary+research+and+education+on+gpu+infrastructure+for+mid%2Dsouth+institutions+at+the+university+of+memphis%3A+Pr)
37. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. [Recursive deep models for semantic compositionality over a sentiment treebank](https://md.research.elamur.ai/free/en/papers/socher-2013-recursive-deep-models-semantic-compositionality/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1631–…
38. Hwanjun Song, Minseok Kim, and Jae-Gil Lee. 2024. Toward robustness in multi-label classification: a data augmentation strategy against imbalance and noise. In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artifi… [find](https://scholar.google.com/scholar?q=Hwanjun+Song%2C+Minseok+Kim%2C+and+Jae%2DGil+Lee%2E+2024%2E+Toward+robustness+in+multi%2Dlabel+classification%3A+a+data+augmentation+strategy+against+imbalance+and+noise%2E+In+Proceedings+of+the+Thirty%2DEighth+AAAI+Co)
39. Carole H. Sudre, Wenqi Li, Tom Vercauteren, Sébastien Ourselin, and M. Jorge Cardoso. 2017. Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. CoRR, abs/1707.03237. — [arXiv:1707.03237](https://arxiv.org/abs/1707.03237) [find](https://scholar.google.com/scholar?q=Carole+H%2E+Sudre%2C+Wenqi+Li%2C+Tom+Vercauteren%2C+S%C3%A9bastien+Ourselin%2C+and+M%2E+Jorge+Cardoso%2E+2017%2E+Generalised+dice+overlap+as+a+deep+learning+loss+function+for+highly+unbalanced+segmentations%2E+CoRR%2C+abs%2F170)
40. Asahi Ushio, Leonardo Neves, Vitor Silva, Francesco. Barbieri, and Jose Camacho-Collados. 2022. Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts. In The 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th I… [find](https://scholar.google.com/scholar?q=Asahi+Ushio%2C+Leonardo+Neves%2C+Vitor+Silva%2C+Francesco%2E+Barbieri%2C+and+Jose+Camacho%2DCollados%2E+2022%2E+Named+Entity+Recognition+in+Twitter%3A+A+Dataset+and+Analysis+on+Short%2DTerm+Temporal+Shifts%2E+In+The+2nd+Co)
41. Ruben van den Goorbergh, Maarten van Smeden, Dirk Timmerman, and Ben Van Calster. 2022. The harm of class imbalance corrections for risk prediction models: illustration and simulation using logistic regression. Journal of the American Medical Informatics Association, 29(9):1525–1534. [find](https://scholar.google.com/scholar?q=Ruben+van+den+Goorbergh%2C+Maarten+van+Smeden%2C+Dirk+Timmerman%2C+and+Ben+Van+Calster%2E+2022%2E+The+harm+of+class+imbalance+corrections+for+risk+prediction+models%3A+illustration+and+simulation+using+logistic+r)
42. Deqing Wang, Hui Zhang, Wenjun Wu, and Mengxiang Lin. 2010. Inverse category frequency based supervised term weighting scheme for text categorization. CoRR, abs/1012.2609. — [arXiv:1012.2609](https://arxiv.org/abs/1012.2609) [find](https://scholar.google.com/scholar?q=Deqing+Wang%2C+Hui+Zhang%2C+Wenjun+Wu%2C+and+Mengxiang+Lin%2E+2010%2E+Inverse+category+frequency+based+supervised+term+weighting+scheme+for+text+categorization%2E+CoRR%2C+abs%2F1012%2E2609%2E+%E2%80%94+%5BarXiv%3A1012%2E2609%5D%28https%3A%2F%2F)
43. Benjamin Warner, Antoine Chaffin, Benjamin Clavié, Orion Weller, Oskar Hallström, Said Taghadouini, Alexis Gallagher, Raja Biswas, Faisal Ladhak, Tom Aarsen, Nathan Cooper, Griffin Adams, Jeremy Howard, and Iacopo Poli. 2024. [Smarter, better, faster, longer: A modern bidirectional encoder for fast,…](https://md.research.elamur.ai/free/en/papers/warner-2024-smarter-better-faster-longer-modern/)
44. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, and 3 others. 2020. [Transf…](https://md.research.elamur.ai/free/en/papers/wolf-2020-transformers-state-art-natural-language/)

*Updated 1 November 2026*