Papers
Topics
Authors
Recent
Assistant
AI Research Assistant
Well-researched responses based on relevant abstracts and paper content.
Custom Instructions Pro
Preferences or requirements that you'd like Emergent Mind to consider when generating responses.
Gemini 2.5 Flash
Gemini 2.5 Flash 158 tok/s
Gemini 2.5 Pro 47 tok/s Pro
GPT-5 Medium 29 tok/s Pro
GPT-5 High 29 tok/s Pro
GPT-4o 117 tok/s Pro
Kimi K2 182 tok/s Pro
GPT OSS 120B 439 tok/s Pro
Claude Sonnet 4.5 38 tok/s Pro
2000 character limit reached

Reduction-based Pseudo-label Generation for Instance-dependent Partial Label Learning (2410.20797v1)

Published 28 Oct 2024 in cs.LG

Abstract: Instance-dependent Partial Label Learning (ID-PLL) aims to learn a multi-class predictive model given training instances annotated with candidate labels related to features, among which correct labels are hidden fixed but unknown. The previous works involve leveraging the identification capability of the training model itself to iteratively refine supervision information. However, these methods overlook a critical aspect of ID-PLL: the training model is prone to overfitting on incorrect candidate labels, thereby providing poor supervision information and creating a bottleneck in training. In this paper, we propose to leverage reduction-based pseudo-labels to alleviate the influence of incorrect candidate labels and train our predictive model to overcome this bottleneck. Specifically, reduction-based pseudo-labels are generated by performing weighted aggregation on the outputs of a multi-branch auxiliary model, with each branch trained in a label subspace that excludes certain labels. This approach ensures that each branch explicitly avoids the disturbance of the excluded labels, allowing the pseudo-labels provided for instances troubled by these excluded labels to benefit from the unaffected branches. Theoretically, we demonstrate that reduction-based pseudo-labels exhibit greater consistency with the Bayes optimal classifier compared to pseudo-labels directly generated from the predictive model.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Learning from partial labels. The Journal of Machine Learning Research, 12:1501–1536, 2011.
  2. Ambiguously labeled learning using dictionaries. IEEE Transactions on Information Forensics and Security, 9(12):2076–2088, 2014.
  3. Maximum margin partial label learning. In Asian conference on machine learning, pages 96–111. PMLR, 2016.
  4. A conditional multinomial mixture model for superset label learning. In Advances in neural information processing systems, pages 548–556. Citeseer, 2012.
  5. Confidence-rated discriminative partial label learning. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 31, 2017.
  6. Learning from candidate labeling sets. Technical report, MIT Press, 2010.
  7. Learning by associating ambiguously labeled images. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 708–715, 2013.
  8. Learning from ambiguously labeled face images. IEEE transactions on pattern analysis and machine intelligence, 40(7):1653–1667, 2017.
  9. Learning with multiple labels. In NIPS, volume 2, pages 897–904. Citeseer, 2002.
  10. Classification with partial labels. In Proceedings of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 551–559, 2008.
  11. Progressive identification of true labels for partial-label learning. In International Conference on Machine Learning, pages 6500–6510. PMLR, 2020.
  12. Provably consistent partial-label learning. arXiv preprint arXiv:2007.08929, 2020.
  13. Exploiting class activation value for partial-label learning. In International Conference on Learning Representations, 2021.
  14. Pico: Contrastive label disambiguation for partial label learning. arXiv preprint arXiv:2201.08984, 2022.
  15. Revisiting consistency regularization for deep partial label learning. In International Conference on Machine Learning, pages 24212–24225. PMLR, 2022.
  16. Learning from ambiguously labeled examples. Intelligent Data Analysis, 10(5):419–439, 2006.
  17. Solving the partial label learning problem: An instance-based approach. In Twenty-fourth international joint conference on artificial intelligence, 2015.
  18. On the robustness of average losses for partial-label learning. arXiv preprint arXiv:2106.06152, 2021.
  19. Instance-dependent partial label learning. Advances in Neural Information Processing Systems, 34, 2021.
  20. Ambiguity-induced contrastive learning for instance-dependent partial label learning. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, Vienna, Austria, pages 3615–3621, 2022.
  21. Decompositional generation process for instance-dependent partial label learning. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net, 2023.
  22. Progressive purification for instance-dependent partial label learning. In International Conference on Machine Learning, pages 38551–38565. PMLR, 2023.
  23. Candidate-aware selective disambiguation based on normalized entropy for instance-dependent partial-label learning. In IEEE/CVF International Conference on Computer Vision, Paris, France, pages 1792–1801, 2023.
  24. Distilling reliable knowledge for instance-dependent partial label learning. In Thirty-Eighth AAAI Conference on Artificial Intelligence, Vancouver, Canada, pages 15888–15896, 2024.
  25. Dive into ambiguity: Latent distribution mining and pairwise uncertainty estimation for facial expression recognition. In IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, virtual, June 19-25, 2021, pages 6248–6257. Computer Vision Foundation / IEEE, 2021.
  26. Partial label learning via feature-aware disambiguation. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pages 1335–1344, 2016.
  27. Lei Feng and Bo An. Leveraging latent label distributions for partial label learning. In IJCAI, pages 2107–2113, 2018.
  28. Adaptive graph guided disambiguation for partial label learning. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 83–91, 2019.
  29. Partial label learning via label enhancement. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 5557–5564, 2019.
  30. Deep discriminative cnn with temporal ensembling for ambiguously-labeled image classification. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, pages 12669–12676, 2020.
  31. Network cooperation with progressive disambiguation for partial label learning. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 471–488. Springer, 2020.
  32. Leveraged weighted loss for partial label learning. In International Conference on Machine Learning, pages 11091–11100. PMLR, 2021.
  33. Partial label learning with semantic label representations. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pages 545–553, 2022.
  34. Deep graph matching for partial label learning. In Proceedings of the International Joint Conference on Artificial Intelligence, pages 3306–3312, 2022.
  35. Alexander B Tsybakov. Optimal aggregation of classifiers in statistical learning. The Annals of Statistics, 32(1):135–166, 2004.
  36. Error-bounded correction of noisy labels. In Proceedings of the 37th International Conference on Machine Learning, Virtual Event, volume 119, pages 11447–11457, 2020.
  37. Meta-weight-net: Learning an explicit mapping for sample weighting. In Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, pages 1917–1928, 2019.
  38. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
  39. Learning multiple layers of features from tiny images. 2009.
  40. Ya Le and Xuan Yang. Tiny imagenet visual recognition challenge. CS 231N, 7(7):3, 2015.
  41. Rank-loss support instance machines for miml instance annotation. In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 534–542, 2012.
  42. Multiple instance metric learning from automatically labeled bags of faces. In European conference on computer vision, pages 634–647. Springer, 2010.
  43. Efficient one pass self-distillation with zipf’s label smoothing. In ECCV, Tel Aviv, Israel, volume 13671, pages 104–119, 2022.
  44. Squeeze, recover and relabel: Dataset condensation at imagenet scale from A new perspective. In Annual Conference on Neural Information Processing Systems, New Orleans, LA, USA, 2023.
  45. A stochastic approximation method. The annals of mathematical statistics, pages 400–407, 1951.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Dice Question Streamline Icon: https://streamlinehq.com

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
Lightbulb Streamline Icon: https://streamlinehq.com

Continue Learning

We haven't generated follow-up questions for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Generate Now
List To Do Tasks Checklist Streamline Icon: https://streamlinehq.com

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up