Skip to main content

Partial Label Learning via Self-Paced Curriculum Strategy

  • Conference paper
  • First Online:
Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 12458))

Abstract

Partial-Label Learning (PLL) aims to learn from the training data, where each example is associated with a set of candidate labels, among which only one is correct. Existing PLL methods to deal with such problem usually treat each training example equally and few works take the complexities of training examples into consideration. In this paper, inspired by the human learning mode that gradually learns from “easy” to “hard”, we propose a novel Self-Paced Curriculum strategy based Partial-Label Learning (SPC-PLL) algorithm, where curriculum strategy can predetermine prior knowledge to adjust the learning priorities of training examples, while self-paced strategy can dynamically select “easy” training examples for model induction according to its current learning progress. The combination of such two strategies is analogous to “instructor-student-collaborative” learning mode, which not only utilizes prior knowledge flexibly but also effectively avoids the inconsistency between the predetermined curriculum and the dynamically learned models. Extensive experimental comparisons and comprehensive ablation study demonstrate the effectiveness of such strategy on solving PLL problem.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    In some literature, partial-label learning is also named as ambiguous label learning [5, 32], superset label learning [19] or soft label learning [27].

  2. 2.

    Our proposed self-paced curriculum strategy can also be well applied to other margin-based PLL methods.

References

  1. Bengio, S., Weston, J., Grangier, D.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9, 1871–1874 (2008)

    Google Scholar 

  2. Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: International Conference on Machine Learning, pp. 41–48 (2009)

    Google Scholar 

  3. Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Britain (2004)

    Book  Google Scholar 

  4. Briggs, F., Fern, X., Raich, R.: Rank-loss support instance machines for MIML instance annotation. In: International Conference on Knowledge Discovery and Data Mining, pp. 534–542 (2012)

    Google Scholar 

  5. Chen, Y., Patel, V., Chellappa, R., Phillips, P.: Ambiguously labeled learning using dictionaries. IEEE Trans. Inf. Forensics Secur. 9, 2076–2088 (2014)

    Article  Google Scholar 

  6. Cour, T., Sapp, B., Taskar, B.: Learning from partial labels. J. Mach. Learn. Res. 12, 1502–1536 (2011)

    Google Scholar 

  7. Feng, L., An, B.: Leveraging latent label distributions for partial label learning. In: International Joint Conference on Artificial Intelligence, pp. 2107–2113 (2018)

    Google Scholar 

  8. Feng, L., An, B.: Partial label learning by semantic difference maximization. In: International Joint Conference on Artificial Intelligence, pp. 2294–2300 (2019)

    Google Scholar 

  9. Feng, L., An, B.: Partial label learning with self-guided retraining. In: AAAI Conference on Artificial Intelligence, pp. 3542–3549 (2019)

    Google Scholar 

  10. Gong, C., Liu, T., Tang, Y., Jian, Y., Jie, Y., Tao, D.: A regularization approach for instance-based superset label learning. IEEE Trans. Cybern. 48, 967–978 (2017)

    Article  Google Scholar 

  11. Guillaumin, M., Verbeek, J., Schmid, C.: Multiple instance metric learning from automatically labeled bags of faces. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6311, pp. 634–647. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15549-9_46

    Chapter  Google Scholar 

  12. Huang, J., et al.: Improving multi-label classification with missing labels by learning label-specific features. Inf. Sci. 492, 124–146 (2019)

    Article  MathSciNet  Google Scholar 

  13. Hüllermeier, E., Beringer, J.: Learning from ambiguously labeled examples. In: Famili, A.F., Kok, J.N., Peña, J.M., Siebes, A., Feelders, A. (eds.) IDA 2005. LNCS, vol. 3646, pp. 168–179. Springer, Heidelberg (2005). https://doi.org/10.1007/11552253_16

    Chapter  Google Scholar 

  14. Jiang, L., Meng, D., Yu, S., Lan, Z., Shan, S., Hauptmann, A.: Self-paced learning with diversity. In: Advances in Neural Information Processing Systems, pp. 2078–2086 (2014)

    Google Scholar 

  15. Jiang, L., Meng, D., Zhao, Q., Shan, S., Hauptmann, A.: Self-paced curriculum learning. In: AAAI Conference on Artificial Intelligence, pp. 2694–2700 (2015)

    Google Scholar 

  16. Khan, F., Mutlu, B., Zhu, J.: How do humans teach: on curriculum learning and teaching dimension. In: Advances in Neural Information Processing Systems, pp. 1449–1457 (2011)

    Google Scholar 

  17. Kumar, M., Packer, B., Koller, D.: Self-paced learning for latent variable models. In: International Conference on Neural Information Processing Systems, pp. 1189–1197 (2010)

    Google Scholar 

  18. Liu, L., Dietterich, T.: A conditional multinomial mixture model for superset label learning. In: Advances in Neural Information Processing Systems, pp. 548–556 (2012)

    Google Scholar 

  19. Liu, L., Dietterich, T.: Learnability of the superset label learning problem. In: International Conference on Machine Learning, pp. 1629–1637 (2014)

    Google Scholar 

  20. Luo, J., Orabona, F.: Learning from candidate labeling sets. In: Advances in Neural Information Processing Systems, pp. 1504–1512 (2010)

    Google Scholar 

  21. Lv, J., Xu, N., Feng, L., Niu, G., Geng, X., Sugiyama, M.: Progressive identification of true labels for partial label learning. In: International Conference on Machine Leaning, pp. 1–10 (2020)

    Google Scholar 

  22. Lyu, G., Feng, S., Huang, W., Dai, G., Zhang, H., Chen, B.: Partial label learning via low-rank representation and label propagation. Soft Comput. 24, 5165–5176 (2020). https://doi.org/10.1007/s00500-019-04269-9

    Article  Google Scholar 

  23. Lyu, G., Feng, S., Li, Y., Jin, Y., Dai, G., Lang, C.: HERA: partial label learning by combining heterogeneous loss with sparse and low-rank regularization. ACM Trans. Intell. Syst. Technol. 11, 1–19 (2020)

    Article  Google Scholar 

  24. Lyu, G., Feng, S., Wang, T., Lang, C.: A self-paced regularization framework for partial label learning. IEEE Trans. Cybern. (2020). https://doi.org/10.1109/TCYB.2020.2990908

    Article  Google Scholar 

  25. Lyu, G., Feng, S., Wang, T., Lang, C., Li, Y.: GM-PLL: graph matching based partial label learning. IEEE Trans. Knowl. Data Eng. (2019). https://doi.org/10.1109/TKDE.2019.2933837

    Article  Google Scholar 

  26. Nguyen, N., Caruana, R.: Classification with partial labels. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 551–559 (2008)

    Google Scholar 

  27. Oukhellou, L., Denux, T., Aknin, P.: Learning from partially supervised data using mixture models and belief functions. Pattern Recogn. 42, 334–348 (2009)

    Article  Google Scholar 

  28. Panis, G., Lanitis, A.: An overview of research activities in facial age estimation using the FG-NET aging database. J. Am. Hist. 5, 455–462 (2015)

    Google Scholar 

  29. Spitkovsky, V., Alshawi, H., Jurafsky, D.: Baby steps: How “less is more" in unsupervised dependency parsing. In: Advances in Neural Information Processing Systems (2009)

    Google Scholar 

  30. Wang, H., Liu, W., Zhao, Y., Hu, T., Chen, K., Chen, G.: Learning from multi-dimensional partial labels. In: International Joint Conference on Artificial Intelligence (2020)

    Google Scholar 

  31. Wang, H., Liu, W., Zhao, Y., Zhang, C., Hu, T., Chen, G.: Discriminative and correlative partial multi-label learning. In: International Joint Conference on Artificial Intelligence, pp. 3691–3697 (2019)

    Google Scholar 

  32. Yao, Y., Feng, J., Chen, X., Gong, C., Wu, J., Yang, J.: Deep discriminative CNN with temporal ensembling for ambiguously-labeled image classification. In: AAAI Conference on Artificial Intelligence, pp. 3542–3549 (2020)

    Google Scholar 

  33. Yu, F., Zhang, M.: Maximum margin partial label learning. Mach. Learn. 106, 573–593 (2017). https://doi.org/10.1007/s10994-016-5606-4

    Article  MathSciNet  MATH  Google Scholar 

  34. Zeng, Z., et al.: Learning by associating ambiguously labeled images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 708–715 (2013)

    Google Scholar 

  35. Zhang, M., Yu, F.: Solving the partial label learning problem: an instance-based approach. In: International Joint Conference on Artificial Intelligence, pp. 4048–4054 (2015)

    Google Scholar 

  36. Zhang, M., Yu, F., Tang, C.: Disambiguation-free partial label learning. IEEE Trans. Knowl. Data Eng. 29, 2155–2167 (2017)

    Article  Google Scholar 

  37. Zhang, M., Zhou, B., Liu, X.: Partial label learning via feature-aware disambiguation. In: International Conference on Knowledge Discovery and Data Mining, pp. 1335–1344 (2016)

    Google Scholar 

  38. Zhou, Y., He, J., Gu, H.: Partial label learning via Gaussian processes. IEEE Trans. Cybern. 47, 4443–4450 (2016)

    Article  Google Scholar 

Download references

Acknowledgement

This work was supported in part by the Fundamental Research Funds for the Central universities (2020YJS026, 2019JBM020), in part by the National Natural Science Foundation of China (No. 61872032), in part by the Beijing Natural Science Foundation (No. 4202058, No. 9192008), and in part by the Key R&D Program of Zhejiang Province (No. 2019C01068).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Songhe Feng .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2021 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Lyu, G., Feng, S., Jin, Y., Li, Y. (2021). Partial Label Learning via Self-Paced Curriculum Strategy. In: Hutter, F., Kersting, K., Lijffijt, J., Valera, I. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2020. Lecture Notes in Computer Science(), vol 12458. Springer, Cham. https://doi.org/10.1007/978-3-030-67661-2_29

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-67661-2_29

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-67660-5

  • Online ISBN: 978-3-030-67661-2

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics