mlsanityData to 7 Oct 2026

Deep Learning for Multi-Label Learning: A Comprehensive Survey

arXiv 2401.16549 ↗First posted 29 Jan 2024cs.LG cs.CVcited by 18

Not on the map. Why?

Abstract (arXiv)

Multi-label learning is a rapidly growing research area that aims to predict multiple labels from a single input data point. In the era of big data, tasks involving multi-label classification (MLC) or ranking present significant and intricate challenges, capturing considerable attention in diverse domains. Inherent difficulties in MLC include dealing with high-dimensional data, addressing label correlations, and handling partial labels, for which conventional methods prove ineffective. Recent years have witnessed a notable increase in adopting deep learning (DL) techniques to address these challenges more effectively in MLC. Notably, there is a burgeoning effort to harness the robust learning capabilities of DL for improved modelling of label dependencies and other challenges in MLC. However, it is noteworthy that comprehensive studies specifically dedicated to DL for multi-label learning are limited. Thus, this survey aims to thoroughly review recent progress in DL for multi-label learning, along with a summary of open research problems in MLC. The review consolidates existing research efforts in DL for MLC,including deep neural networks, transformers, autoencoders, and convolutional and recurrent architectures. Finally, the study presents a comparative analysis of the existing methods to provide insightful observations and stimulate future research directions in this domain.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 58 of its 210 references that are in the map. First posted on arXiv 29 Jan 2024.

Builds on

58 of 210 references.

References · 58

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  6. 2014Convolutional Neural Networks for Sentence Classificationcited by 1,124
  7. 2019Multi-Label Image Recognition with Graph Convolutional Networkscited by 320
  8. 2016CNN-RNN: A Unified Framework for Multi-label Image Classificationcited by 189
  9. 2020General Multi-label Image Classification with Transformerscited by 126
  10. 2021Query2Label: A Simple Transformer Way to Multi-Label Classificationcited by 126
  11. 2019Learning a Deep ConvNet for Multi-label Classification with Partial Labelscited by 124
  12. 2019Learning Semantic-Specific Graph Representation for Multi-Label Image Recognitioncited by 116
38 more
  1. 2018AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classificationcited by 101
  2. 2015Learning to Diagnose with LSTM Recurrent Neural Networkscited by 99
  3. 2020The Emerging Trends of Multi-Label Learningcited by 99
  4. 2018SGM: Sequence Generation Model for Multi-label Classificationcited by 89
  5. 2017Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classificationcited by 85
  6. 2021ML-Decoder: Scalable and Versatile Classification Headcited by 78
  7. 2017Multi-Label Zero-Shot Learning with Structured Knowledge Graphscited by 72
  8. 2019Multi-Label Classification with Label Graph Superimposingcited by 65
  9. 2022Delving into Masked Autoencoders for Multi-Label Thorax Disease Classificationcited by 65
  10. 2014CNN: Single-label to Multi-labelcited by 62
  11. 2013Deep Convolutional Ranking for Multilabel Image Annotationcited by 47
  12. 2019Orderless Recurrent Models for Multi-label Classificationcited by 46
  13. 2017Recurrent Attentional Reinforcement Learning for Multi-label Image Recognitioncited by 44
  14. 2017Improving Pairwise Ranking for Multi-label Image Classificationcited by 40
  15. 2015Exploit Bounding Box Annotations for Multi-label Object Recognitioncited by 39
  16. 2017Multi-Label Learning with Global and Local Label Correlationcited by 39
  17. 2021Comprehensive Comparative Study of Multi-Label Classification Methodscited by 38
  18. 2021DeepXML: A Deep Extreme Multi-Label Learning Framework Applied to Short Text Documentscited by 37
  19. 2013Large-scale Multi-label Text Classification - Revisiting Neural Networkscited by 35
  20. 2017Order-Free RNN with Visual Attention for Multi-Label Classificationcited by 26
  21. 2020Disentangled Variational Autoencoder based Multi-Label Classification with Covariance-Aware Multivariate Probit Modelcited by 22
  22. 2017Learning Deep Latent Spaces for Multi-Label Classificationcited by 21
  23. 2021MlTr: Multi-label Classification with Transformercited by 21
  24. 2022Multi-Label Retinal Disease Classification using Transformerscited by 18
  25. 2018Recurrently Exploring Class-wise Attention in A Hybrid Convolutional and Bidirectional LSTM Network for Multi-label Aerial Image Classificationcited by 17
  26. 2018ML-Net: multi-label classification of biomedical texts with deep neural networkscited by 17
  27. 2023Multi-Label Self-Supervised Learning with Scene Imagescited by 17
  28. 2022ZLPR: A Novel Loss for Multi-label Classificationcited by 16
  29. 2021Gaussian Mixture Variational Autoencoder with Contrastive Learning for Multi-Label Classificationcited by 15
  30. 2016Semantic Regularisation for Recurrent Image Annotationcited by 14
  31. 2015Learning Structured Inference Neural Networks with Label Relationscited by 13
  32. 2022Graph Attention Transformer Network for Multi-Label Image Classificationcited by 11
  33. 2016Annotation Order Matters: Recurrent Image Annotator for Arbitrary Length Image Taggingcited by 8
  34. 2023MASK-CNN-Transformer For Real-Time Multi-Label Weather Recognitioncited by 8
  35. 2022Multi-label Classification with High-rank and High-order Label Correlationscited by 7
  36. 2023An Attention-based Approach to Hierarchical Multi-label Music Instrument Classificationcited by 7
  37. 2019Ranking-Based Autoencoder for Extreme Multi-label Classificationcited by 6
  38. 2020A multimodal approach for multi-label movie genre classificationcited by 6

50 most cited of 58 All 58 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 6; 2026: 8.

18 papers.

Sort:

By area:

  1. 2025MAT-Agent: Adaptive Multi-Agent Training Optimizationcited by 34
  2. 2024Correlation-Aware Graph Convolutional Networks for Multi-Label Node Classificationcited by 11
  3. 2025SATA-BENCH: Select All That Apply Benchmark for Multiple Choice Questionscited by 9
  4. 2026MILD: Multi-Intent Learning and Disambiguation for Proactive Failure Prediction in Intent-based Networkingcited by 2
  5. 2025Large Language Models for Zero-Shot Multicultural Name Recognitioncited by 1
  6. 2025Divide, Cache, Conquer: Dichotomic Prompting for Efficient Multi-Label LLM-Based Classificationcited by 1
  7. 2026KVpop -- Key-Value Cache Compression with Predictive Online Pruningcited by 1
  8. 2024A Survey on Incomplete Multi-label Learning: Recent Advances and Future Trendscited by 0
  9. 2024Dual-Label Learning With Irregularly Present Labelscited by 0
  10. 2024Your Next State-of-the-Art Could Come from Another Domain: A Cross-Domain Analysis of Hierarchical Text Classificationcited by 0
  11. 2025Identifying Obfuscated Code through Graph-Based Semantic Analysis of Binary Codecited by 0
  12. 2025Out-of-Distribution Detection via Channelwise Feature Aggregation in Neural Network-Based Receiverscited by 0
6 more
  1. 2026D2ACE: Multi-Label Batch Selection Guided by Dual Dynamics and Adaptive Correlation Enhancementcited by 0
  2. 2026Principled Algorithms for Optimizing Generalized Metrics in Multi-Label Learningcited by 0
  3. 2026Peak-Based Nuclide Identification in HPGe γ-Spectrometry with Machine Learning and SHAPcited by 0
  4. 2026Rethinking Multi-Label Image Classification With Deep Learning: Taxonomy, Challenge, and Outlookcited by 0
  5. 2026Untangling Co-Drift: Proactive Multi-Intent Failure Prediction and Root-Cause Disambiguation for Self-Driving Networkscited by 0
  6. 2026LightTeaNet: A Weakly Supervised Lightweight CNN for Multi-Label Tea Leaf Disease Detection and Localizationcited by 0