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.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Bengio, S., Weston, J., Grangier, D.: LIBLINEAR: a library for large linear classification. J. Mach. Learn. Res. 9, 1871–1874 (2008)
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: International Conference on Machine Learning, pp. 41–48 (2009)
Boyd, S., Vandenberghe, L.: Convex Optimization. Cambridge University Press, Britain (2004)
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)
Chen, Y., Patel, V., Chellappa, R., Phillips, P.: Ambiguously labeled learning using dictionaries. IEEE Trans. Inf. Forensics Secur. 9, 2076–2088 (2014)
Cour, T., Sapp, B., Taskar, B.: Learning from partial labels. J. Mach. Learn. Res. 12, 1502–1536 (2011)
Feng, L., An, B.: Leveraging latent label distributions for partial label learning. In: International Joint Conference on Artificial Intelligence, pp. 2107–2113 (2018)
Feng, L., An, B.: Partial label learning by semantic difference maximization. In: International Joint Conference on Artificial Intelligence, pp. 2294–2300 (2019)
Feng, L., An, B.: Partial label learning with self-guided retraining. In: AAAI Conference on Artificial Intelligence, pp. 3542–3549 (2019)
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)
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
Huang, J., et al.: Improving multi-label classification with missing labels by learning label-specific features. Inf. Sci. 492, 124–146 (2019)
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
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)
Jiang, L., Meng, D., Zhao, Q., Shan, S., Hauptmann, A.: Self-paced curriculum learning. In: AAAI Conference on Artificial Intelligence, pp. 2694–2700 (2015)
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)
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)
Liu, L., Dietterich, T.: A conditional multinomial mixture model for superset label learning. In: Advances in Neural Information Processing Systems, pp. 548–556 (2012)
Liu, L., Dietterich, T.: Learnability of the superset label learning problem. In: International Conference on Machine Learning, pp. 1629–1637 (2014)
Luo, J., Orabona, F.: Learning from candidate labeling sets. In: Advances in Neural Information Processing Systems, pp. 1504–1512 (2010)
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)
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
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)
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
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
Nguyen, N., Caruana, R.: Classification with partial labels. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 551–559 (2008)
Oukhellou, L., Denux, T., Aknin, P.: Learning from partially supervised data using mixture models and belief functions. Pattern Recogn. 42, 334–348 (2009)
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)
Spitkovsky, V., Alshawi, H., Jurafsky, D.: Baby steps: How “less is more" in unsupervised dependency parsing. In: Advances in Neural Information Processing Systems (2009)
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)
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)
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)
Yu, F., Zhang, M.: Maximum margin partial label learning. Mach. Learn. 106, 573–593 (2017). https://doi.org/10.1007/s10994-016-5606-4
Zeng, Z., et al.: Learning by associating ambiguously labeled images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 708–715 (2013)
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)
Zhang, M., Yu, F., Tang, C.: Disambiguation-free partial label learning. IEEE Trans. Knowl. Data Eng. 29, 2155–2167 (2017)
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)
Zhou, Y., He, J., Gu, H.: Partial label learning via Gaussian processes. IEEE Trans. Cybern. 47, 4443–4450 (2016)
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
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
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)