Long-Tail Learning

Ask about this topic

Overview

Long-tail learning studies how to recognize rare classes, events, and behaviors when training data is dominated by frequent examples. Common approaches include reweighting losses or logits, resampling and generating data, separating representation learning from classification, and using experts, distillation, or semantic priors to support underrepresented categories. Researchers evaluate these methods across settings such as image recognition, medical data, language models, recommendation, and federated learning, often measuring tail accuracy alongside overall accuracy or macro-F1. The central challenge is improving rare-case performance without degrading frequent classes, especially when labels are noisy, data is sparse or shifted, and aggregate scores conceal consequential failures.

Latest papers

CardsList

50 papers4 papers in the last four weeks, down 43% on the four weeks before. 0.0% of all new papers.

  1. Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data

    Oct 23, 2026Joonhyeok Jeong, Jy-yong Sohn, Kibok LeeContrastive LearningSupervised Contrastive Learning

    Department of Statistics and Data Science, Yonsei University

  2. Overcoming Prior Barriers: Supervised Fine-Tuning under Long-Tail Distribution

    Oct 8, 2026Haohui Wang, Jiahao Xu, Wangzhi Zhan +9Supervised Fine-TuningInstruction-Tuning Data Selection

    Virginia Tech · Amazon · Meta +2

  3. Unsupervised Long-Tailed Adaptation of Vision-Language Models

    Oct 6, 2026Keliang Chen, Yaxin Hou, Hui Liu +1Long-Tail LearningVLM Adaptation

    School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · School of Computing and Information Sciences, Saint Francis University, Hong Kong, China · Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China

  4. OFBD: Object-Focused Background Debiasing for Long-Tailed Learning

    Sep 29, 2026Shenghan Chen, Yiming Liu, Zhipeng Deng +6Long-Tailed ClassificationLong-Tail Learning

    Westlake University, Hangzhou, China · Shandong University, Jinan, China · Hokkaido University, Sapporo, Japan +1

  5. EHRAdapt: Adapting Pretrained Language Models to Electronic Health Records with Semantic Priors for Rare Clinical Events

    Sep 27, 2026Andre R Goncalves, Vincent Liu, Priyadip RayDomain Adaptation for LLMsLong-Tail Learning

    Lawrence Livermore National Laboratory · Kaiser Permanente

  6. When Noise Meets Long-Tail: Feature-Threshold Dual Calibration for Robust Pseudo-Labeling

    Sep 27, 2026Ping Guo, Zhiqi Huang, Xinran LiImage SegmentationLong-Tail Learning

    Graduate School of Information, Production and Systems, Waseda University, Kitakyushu, Japan · School of Software, Dalian University of Technology, Dalian, China · School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen, China

  7. Less Is More in the Long Tail: Stage-Adaptive Sample Selection for Annotation-Efficient Dense Prediction

    Sep 22, 2026Xiaofei Du, Lei Zhang, Shuyu Yan +2Active LearningData-Efficient Learning

    Digital Medical Research Center, School of Basic Medical Sciences, Fudan University, Shanghai 200032, China · Shanghai Key Laboratory of Medical Image Computing and Computer Assisted Intervention, Shanghai 200032, China · Frontier Innovation Center, Department of Systems Biology for Medicine, Qidong-Fudan Innovative Institute of Medical Sciences, School of Basic Medical Sciences, Zhongshan Hospital Clinical Center for Biotherapy, Fudan University, Shanghai 200032, China +1

  8. Long-Tail Rebalancing for Non-Verbal Vocalization-Aware ASR: A Track 1 System for the NVVSpeech Challenge

    Sep 20, 2026Shangyue Jia, Jingru Ma, Yangzhuo Li +9Long-Tail LearningAutomatic Speech Recognition

    School of Intelligence Science and Technology, Nanjing University · Jilin University · Beijing Institute of Technology +3

  9. Bounded Adjustment with Reliability-Guided Embedding for Imbalanced Learning with Noisy Labels

    Sep 14, 2026Mushir Akhtar, Akarsh J., M. Tanveer +1Class-Imbalanced LearningLong-Tail Learning

    Department of Mathematics, Indian Institute of Technology Indore, India · Department of Electrical Engineering, Indian Institute of Technology Indore, India

  10. Long-Tail Adaptive Flow Matching with Explicit Conditional Consistency Guidance for Precise Multimodal Face Synthesis

    Sep 14, 2026Yushe Cao, Xuechao Zou, Xing Xi +3Multimodal GenerationDiffusion Model Guidance

    Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China · School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China · School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China +1

  11. Generalized Biomedicine Discovery

    Sep 9, 2026Luyao Tang, Yingkai Yang, Hanqi Chen +3Generalized Category DiscoveryMedical Image Anomaly Detection

    The University of Hong Kong, Hong Kong SAR, China · Shenzhen University, Shenzhen, China · Xiamen University, Xiamen, China

  12. Exposing the Long-tail in Embodied Urban Navigation via Scalable Learning from In-the-Wild Videos

    Aug 17, 2026Bingyi Xia, Han Bao, Zhewei Chen +5Embodied NavigationRobot Navigation

    Southern University of Science and Technology · The Hong Kong University of Science and Technology · Peng Cheng Laboratory

  13. From Perturbation Correction to Geometry-Aware Sampling: Sharpness-Guided Equilibrium Sampling for Balanced Flat Minima in Long-Tailed Learning

    Jul 24, 2026Jiaxin Deng, Junbiao PangSharpness-Aware MinimizationLong-Tail Learning

    School of Information Science and Technology, Beijing University of Technology, Beijing, China

  14. Greedy Volume Maximization of Gradient Embeddings for Long-Tailed Frame-Level Bioacoustic Active Learning

    Jul 15, 2026Shiqi Zhang, Marius Faiß, Ariana Strandburg-Peshkin +1Long-Tail LearningActive Learning

    1Audio Research Group, Tampere University, Tampere, Finland · Department for the Ecology of Animal Societies, Max Planck Institute of Animal Behavior · 3International Max Planck Research School for Quantitative Behavior, Ecology and Evolution +1

  15. AdaPCLA: Adaptive Prior-Calibrated Logit Adjustment for Long-Tailed Longitudinal EHR Generation

    Jul 14, 2026Shuai Cui, Chen Wenxuan, Wenjie Du +3Logit AdjustmentLong-Tail Learning

    University of Science and Technology of China · Sun Yat-sen University

  16. Prior-Anchored Debiasing for Long-Tailed Multi-Organ Pathology Report Generation

    Jul 1, 2026Feng Yang, Jie Liu, Yubo Pang +5Medical Report GenerationLong-Tail Learning

    City University of Hong Kong, Hong Kong SAR · University of Nottingham, United Kingdom · University of Massachusetts Boston, United States

  17. Latent-CURE for Breast Cancer Diagnosis

    Jun 29, 2026Weiyi Zhao, Xiaoyu Tan, Lu Gan +2Breast CancerLong-Tail Learning

    School of Electronic and Electrical Engineering, Shanghai University of Engineering Science, Shanghai 201620, China · Tencent YouTu Lab, Shanghai 200232, China · Integrative Clinical Research Ward, Clinical Medicine Research Institute, Zhongshan Hospital, Fudan University, Shanghai 200032, China

  18. Narrative-UFET: Narrative Generation for Ultra-Fine Entity Typing

    Jun 25, 2026Mreedul Gupta, Advait Deshmukh, Ashwin Umadi +2Long-Tail LearningNarrative Generation

    University of Colorado Boulder

  19. Towards Federated Long-Tailed Graph Learning: An Energy-Guided Dual Decoupling Approach

    Jun 23, 2026Lianshuai Guo, Zhongzheng Yuan, Xunkai Li +2Graph Structure LearningLong-Tail Learning

    Shandong University, School of Airspace Science and Engineering, Weihai 264209, China · Beijing Institute of Technology, School of Computer Science and Technology, Beijing 100081, China

  20. Gen2Balance: Generative Balancing for Long-Tailed Video Action Recognition

    Jun 21, 2026Prajwal Gatti, Simon Jenni, Fabian Caba Heilbron +1Synthetic Data AugmentationLong-Tail Learning

    University of Bristol · 2Adobe Research

  21. Toward Multi-Domain and Long-Tailed Quantization via Feature Alignment and Scaling

    Jun 3, 2026Ting-An Chen, Chin-Yuan Yeh, De-Nian YangLong-Tail LearningLow-Bit Quantization

    Graduate Institute of Electrical Engineering, National Taiwan University, Taiwan · Institute of Information Science, Academia Sinica, Taiwan · Graduate Institute of Communication Engineering, National Taiwan University, Taiwan +1

  22. BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation

    Jun 2, 2026Xi Zhou, Famin Wu, Mingming Li +4Adaptive Knowledge DistillationSequential Recommendation

    Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · Beijing Institute for General Artificial Intelligence, Beijing, China

  23. DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning

    May 28, 2026Hyuck Lee, Taemin Park, Heeyoung KimClass-Imbalanced LearningLong-Tail Learning

    AI Research, Krafton, Teheran-ro 231, Centerfield EAST, Gangnam-gu, Seoul, 06142, Republic of Korea · Department of Industrial and Systems Engineering, Korea Advanced Institute of Science and Technology (KAIST), 291 Daehak-ro, Yuseong-gu, Daejeon, 34141, Republic of Korea

  24. Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention

    May 28, 2026Jing Huang, Daniel Wurgaft, Rachit Bansal +6Long-Tail LearningLanguage Model Scaling Laws

    Stanford University · Kempner Institute at Harvard University · MIT +1

  25. Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors

    May 20, 2026Siqi Wei, Hongbin Xu, Feng Xiao +43D Point Cloud SegmentationLong-Tail Learning

    South China University of Technology · Bytedance · Tsinghua University +2

  26. When Irregularity Helps: A Subclass Analysis of Inductive Bias in Neural Morphology

    May 19, 2026Wen ZhangNeural Network GeneralizationLong-Tail Learning

  27. Balancing Knowledge Distillation for Imbalance Learning with Bilevel Optimization

    May 18, 2026Anh B. H. Nguyen, Ba Tho Phan, Viet Cuong TaClass-Imbalanced LearningLong-Tail Learning

    VNU University of Engineering and Technology, Hanoi, Vietnam

  28. Flow Matching with Optimized Subclass Priors for Medical Image Augmentation

    May 15, 2026Felix Nützel, Mischa Dombrowski, Bernhard KainzFlow MatchingSynthetic Data Augmentation

    Department of Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91052 Erlangen, Germany · Department of Computing, Imperial College London, London SW7 2AZ, UK

  29. BiFedKD: Bidirectional Federated Knowledge Distillation Framework for Non-IID and Long-Tailed ECG Monitoring

    May 14, 2026Zixuan Shu, Tiancheng Cao, Hen-Wei HuangLong-Tail LearningCommunication-Efficient Distributed Training

    School of Electrical and Electronic Engineering, Nanyang Technological University, Republic of Singapore · Lee Kong Chian School of Medicine, Nanyang Technological University, Republic of Singapore

  30. Taming the Long Tail: Rebalancing Adversarial Training via Adaptive Perturbation

    May 13, 2026Lilin Zhang, Yimo Guo, Yue Li +2Adversarial TrainingClass-Imbalanced Learning

    1Sichuan University · 2Dongfang Electric (Chengdu) Innovation Research Co., Ltd. · 3Southwest China Research Institute of Electronic Equipment