mlsanityData to 14 Oct 2026

A Survey on Extreme Multi-label Learning

arXiv 2210.03968 ↗First posted 8 Oct 2022cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Multi-label learning has attracted significant attention from both academic and industry field in recent decades. Although existing multi-label learning algorithms achieved good performance in various tasks, they implicitly assume the size of target label space is not huge, which can be restrictive for real-world scenarios. Moreover, it is infeasible to directly adapt them to extremely large label space because of the compute and memory overhead. Therefore, eXtreme Multi-label Learning (XML) is becoming an important task and many effective approaches are proposed. To fully understand XML, we conduct a survey study in this paper. We first clarify a formal definition for XML from the perspective of supervised learning. Then, based on different model architectures and challenges of the problem, we provide a thorough discussion of the advantages and disadvantages of each category of methods. For the benefit of conducting empirical studies, we collect abundant resources regarding XML, including code implementations, and useful tools. Lastly, we propose possible research directions in XML, such as new evaluation metrics, the tail label problem, and weakly supervised XML.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 63 of its 164 references that are in the map. First posted on arXiv 8 Oct 2022.

Builds on

63 of 164 references.

References · 63

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Prototypical Networks for Few-shot Learningcited by 3,015
  5. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,811
  6. 2016Matching Networks for One Shot Learningcited by 2,255
  7. 2015Effective Approaches to Attention-based Neural Machine Translationcited by 1,026
  8. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  9. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 861
  10. 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 809
  11. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  12. 2015Image-based Recommendations on Styles and Substitutescited by 706
38 more
  1. 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 705
  2. 2019Latent Retrieval for Weakly Supervised Open Domain Question Answeringcited by 695
  3. 2019Adversarial Training for Free!cited by 643
  4. 2020Long-tail learning via logit adjustmentcited by 618
  5. 2015Bidirectional LSTM-CRF Models for Sequence Taggingcited by 546
  6. 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
  7. 2020Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classificationcited by 175
  8. 2014Label Distribution Learningcited by 124
  9. 2019Large-Scale Multi-Label Text Classification on EU Legislationcited by 104
  10. 2015Inferring Networks of Substitutable and Complementary Productscited by 92
  11. 2016DiSMEC - Distributed Sparse Machines for Extreme Multi-label Classificationcited by 71
  12. 2021Fast Multi-Resolution Transformer Fine-tuning for Extreme Multi-label Text Classificationcited by 67
  13. 2018Imbalanced Deep Learning by Minority Class Incremental Rectificationcited by 65
  14. 2019Bonsai -- Diverse and Shallow Trees for Extreme Multi-label Classificationcited by 61
  15. 2013Large-scale Multi-label Learning with Missing Labelscited by 58
  16. 2020PECOS: Prediction for Enormous and Correlated Output Spacescited by 50
  17. 2021ECLARE: Extreme Classification with Label Graph Correlationscited by 38
  18. 2021DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documentscited by 37
  19. 2019Extreme Classification in Log Memory using Count-Min Sketch: A Case Study of Amazon Search with 50M Productscited by 36
  20. 2021DECAF: Deep Extreme Classification with Label Featurescited by 33
  21. 2022NGAME: Negative Mining-aware Mini-batching for Extreme Classificationcited by 32
  22. 2018Stochastic Negative Mining for Learning with Large Output Spacescited by 29
  23. 2019Extreme Multi-Label Legal Text Classification: A case study in EU Legislationcited by 26
  24. 2020Pretrained Generalized Autoregressive Model with Adaptive Probabilistic Label Clusters for Extreme Multi-label Text Classificationcited by 25
  25. 2017Deep Extreme Multi-label Learningcited by 24
  26. 2015LSHTC: A Benchmark for Large-Scale Text Classificationcited by 22
  27. 2017Learning Deep Latent Spaces for Multi-Label Classificationcited by 21
  28. 2021Extreme Zero-Shot Learning for Extreme Text Classificationcited by 15
  29. 2022On Missing Labels, Long-tails and Propensities in Extreme Multi-label Classificationcited by 15
  30. 2022Open Vocabulary Extreme Classification Using Generative Modelscited by 13
  31. 2016Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimationcited by 10
  32. 2020Extreme Classification via Adversarial Softmax Approximationcited by 10
  33. 2020Multi-Label Sampling based on Local Label Imbalancecited by 10
  34. 2021Large-Scale Training System for 100-Million Classification at Alibabacited by 10
  35. 2021Propensity-scored Probabilistic Label Treescited by 8
  36. 2014Logarithmic Time Online Multiclass predictioncited by 7
  37. 2018Efficient Loss-Based Decoding on Graphs For Extreme Classificationcited by 7
  38. 2019Accelerating Extreme Classification via Adaptive Feature Agglomerationcited by 7

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 3; 2024: 3; 2025: 0; 2026: 1.

7 papers.

  1. 2023Deep Partial Multi-Label Learning with Graph Disambiguationcited by 5
  2. 2024Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classificationcited by 1
  3. 2023Label Embedding via Low-Coherence Matricescited by 0
  4. 2023When Measures are Unreliable: Imperceptible Adversarial Perturbations toward Top-k Multi-Label Learningcited by 0
  5. 2024Graph Residual based Method for Molecular Property Predictioncited by 0
  6. 2024Your Next State-of-the-Art Could Come from Another Domain: A Cross-Domain Analysis of Hierarchical Text Classificationcited by 0
  7. 2026Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlookcited by 0