Journal of Computer Science and Technology ›› 2021, Vol. 36 ›› Issue (3): 590-605.doi: 10.1007/s11390-021-0992-x

Special Issue: Artificial Intelligence and Pattern Recognition

• Special Section on Learning from Small Samples • Previous Articles     Next Articles

Partial Label Learning via Conditional-Label-Aware Disambiguation

Peng Ni, Su-Yun Zhao*, Member, CCF, Zhi-Gang Dai, Hong Chen, Distinguished Member, CCF, and Cui-Ping Li, Distinguished Member, CCF        

  1. Key Laboratory of Data Engineering and Knowledge Engineering(Renmin University of China), Ministry of Education Beijing 100087, China;School of Information, Renmin University of China, Beijing 100087, China
  • Received:2020-09-15 Revised:2021-04-22 Online:2021-05-05 Published:2021-05-31
  • Contact: Su-Yun Zhao E-mail:zhaosuyun@ruc.edu.cn
  • About author:Peng Ni achieved his Master's degree in computer application technology from Renmin University of China, Beijing, in 2020. His research interests include machine learning, uncertain artificial intelligence, and incremental feature selection method based on fuzzy rough sets.
  • Supported by:
    The work was supported by the National Key Research & Develop Plan of China under Grant Nos. 2017YFB1400700 and 2018YFB1004401, and the National Natural Science Foundation of China under Grant Nos. 61732006, 61702522, 61772536, 61772537, 62076245, and 62072460, and Beijing Natural Science Foundation under Grant No. 4212022.

Partial label learning is a weakly supervised learning framework in which each instance is associated with multiple candidate labels, among which only one is the ground-truth label. This paper proposes a unified formulation that employs proper label constraints for training models while simultaneously performing pseudo-labeling. Unlike existing partial label learning approaches that only leverage similarities in the feature space without utilizing label constraints, our pseudo-labeling process leverages similarities and differences in the feature space using the same candidate label constraints and then disambiguates noise labels. Extensive experiments on artificial and real-world partial label datasets show that our approach significantly outperforms state-of-the-art counterparts on classification prediction.

Key words: disambiguation; partial label learning; similarity and dissimilarity; weak supervision;

[1] Cour T, Sapp B, Taskar B. Learning from partial labels. Journal of Machine Learning Research, 2011, 12:1501-1536.
[2] Chen Y C, Patel V M, Chellappa R, Phillips P J. Ambiguously labeled learning using dictionaries. IEEE Transactions on Information Forensics and Security, 2014, 9(12):2076-2088. DOI:10.1109/TIFS.2014.2359642.
[3] Zhang M L, Zhou B B, Liu X Y. Partial label learning via feature-aware disambiguation. In Proc. the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2016, pp.1335-1344. DOI:10.1145/2939672.2939788.
[4] Dong X B, Yu Z W, Cao W M, Shi Y F, Ma Q L. A survey on ensemble learning. Frontiers of Computer, 2020, 14(2):241-258. DOI:10.1007/s11704-019-8208-z.
[5] Zhang M L, Li Y K, Liu X Y. Binary relevance for multilabel learning:An overview. Frontiers of Computer Science, 2018, 12(2):191-202. DOI:10.1007/s11704-017-7031-7.
[6] Xu S, Yang M, Zhou Y, Zheng R, Liu W, He J. Partial label metric learning by collapsing classes. International Journal of Machine Learning and Cybernetics, 2020, 11:2453-2460. DOI:10.1007/s13042-020-01129-z.
[7] Luo J, Orabona F. Learning from candidate labeling sets. In Proc. the 24th Annual Conference on Neural Information Processing Systems, December 2010, pp.1504-1512.
[8] Zeng Z, Xiao S, Jia K, Chan T H, Gao S, Xu D, Ma Y. Learning by associating ambiguously labeled images. In Proc. the 2013 IEEE Conference on Computer Vision and Pattern Recognition, June 2013, pp.708-715. DOI:10.1109/CVPR.2013.97.
[9] Liu L, Dietterich T G. A conditional multinomial mixture model for superset label learning. In Proc. the 25th International Conference on Neural Information Processing Systems, December 2012, pp.548-556.
[10] Zhang M L, Yu F, Tang C Z. Disambiguation free partial label learning. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(10):2155-2167. DOI:10.1109/TKDE.2017.2721942.
[11] Hüllermeier E, Beringer J. Learning from ambiguously labeled examples. Intelligent Data Analysis, 2006, 10(5):419-439. DOI:10.3233/IDA-2006-10503.
[12] Zhang M L, Yu F. Solving the partial label learning problem:An instance-based approach. In Proc. the 24th International Joint Conference on Artificial Intelligence, July 2015, pp.4048-4054.
[13] Jin R, Ghahramani Z. Learning with multiple labels. In Proc. the 15th International Conference on Neural Information Processing Systems, January 2003, pp.921-928.
[14] Nguyen N, Caruana R. Classification with partial labels. In Proc. the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2008, pp.551-559. DOI:10.1145/1401890.1401958.
[15] Feng L, An B. Leveraging latent label distributions for partial label learning. In Proc. the 27th International Joint Conference on Artificial Intelligence, July 2018, pp.2107-2113. DOI:10.24963/ijcai.2018/291.
[16] Wang D B, Li L, Zhang M L. Adaptive graph guided disambiguation for partial label learning. In Proc. the 25th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, July 2019, pp.83-91. DOI:10.1145/3292500.3330840.
[17] Tang C Z, Zhang M L. Confidence-rated discriminative partial label learning. In Proc. the 31st AAAI Conference on Artificial Intelligence, February 2017, pp. 2611-2617.
[18] Yu F, Zhang M L. Maximum margin partial label learning. Machine Learning, 2017, 106(4):573-593. DOI:10.1007/s10994-016-5606-4.
[19] Xu N, Lv J, Geng X. Partial label learning via label enhancement. In Proc. the 33rd AAAI Conference on Artificial Intelligence, January 27-February 1, 2019. DOI:10.1609/aaai.v33i01.33015557.
[20] Feng L, An B. Partial label learning by semantic difference maximization. In Proc. the 28th International Joint Conference on Artificial Intelligence, August 2019, pp.2294-2300. DOI:10.24963/ijcai.2019/318.
[21] Xie M K, Huang S J. Partial multi-label learning. In Proc. the 32nd AAAI Conference on Artificial Intelligence, February 2018, pp.4302-4309.
[22] Yu G, Chen X, Domeniconi C, Wang J, Li Z, Zhang Z, Wu X. Feature-induced partial multilabel learning. In Proc. the 2018 IEEE International Conference on Data Mining, November 2018, pp.1398-1403. DOI:10.1109/ICDM.2018.00192.
[23] Fang J P, Zhang M L. Partial multi-label learning via credible label elicitation. In Proc. the 33rd AAAI Conference on Artificial Intelligence, January 27-February 1, 2019, pp.3518-3525. DOI:10.1609/aaai.v33i01.33013518.
[24] Sun L, Feng S, Wang T, Lang C, Jin Y. Partial multilabel learning by low-rank and sparse decomposition. In Proc. the 33rd AAAI Conference on Artificial Intelligence, January 27-February 1, 2019, pp.5016-5023. DOI:10.1609/aaai.v33i01.33015016.
[25] Sun L, Ge H W, Kang W J. Non-negative matrix factorization based modeling and training algorithm for multi-label learning. Frontiers of Computer Science, 2019, 13(6):1243-1254. DOI:10.1007/s11704-018-7452-y.
[26] Schölkopf B, Smola A J. Learning with Kernels:Support Vector Machines, Regularization, Optimization, and Beyond (1st edition). The MIT Press, 2001.
[27] Yuille A L, Rangarajan A. The concave-convex procedure. Neural Computation, 2003, 15(4):915-936. DOI:10.1162/08997660360581958.
[28] Sriperumbudur B K, Torres D A, Lanckriet G R. A majorization-minimization approach to the sparse generalized eigenvalue problem. Machine Learning, 2011, 85(1/2):3-39. DOI:10.1007/s10994-010-5226-3.
[29] Gong C, Liu T, Tang Y, Yang J, Yang J, Tao D. A regularization approach for instance-based superset label learning. IEEE Transactions on Cybernetics, 2018, 48(3):967-978. DOI:10.1109/TCYB.2017.2669639.
[30] Sriperumbudur B K, Lanckriet G R. On the convergence of the concave-convex procedure. In Proc. the 23rd International Conference on Neural Information Processing Systems, December 2009, pp.1759-1767.
[31] Guillaumin M, Verbeek J, Schmid C. Multiple instance metric learning from automatically labeled bags of faces. In Proc. the 11th European Conference on Computer Vision, September 2010, pp.634-647. DOI:10.1007/978-3-642-15549-9_46.
[32] Briggs F, Fern X Z, Raich R. Rank-loss support instance machines for MIML instance annotation. In Proc. the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 2012, pp.534-542. DOI:10.1145/2339530.2339616.
[1] Chen-Chen Sun, De-Rong Shen, Yue Kou, Tie-Zheng Nie, Ge Yu. Topological Features Based Entity Disambiguation [J]. , 2016, 31(5): 1053-1068.
[2] Dan Yang, De-Rong Shen, Ge Yu, Yue Kou, and Tie-Zheng Nie. Query Intent Disambiguation of Keyword-Based Semantic Entity Search in Dataspaces [J]. , 2013, 28(2): 382-393.
[3] Javier Tejada-Cárcamo, Hiram Calvo, Alexander Gelbukh, and Kazuo Hara. Unsupervised WSD by Finding the Predominant Sense Using Context as a Dynamic Thesaurus [J]. , 2010, 25(5): 1030-1039.
[4] MENG Xiaofeng; LIU Shuang; WANG Shan;. Word Segmentation Based on Database Semanticsin NChiql [J]. , 2000, 15(4): 346-354.
[5] MENG Xiaofeng(孟小峰),LIU Shuang(刘爽)and WANG Shan(王珊). Word Segmentation Based on Database Semantics in Nchiql [J]. , 2000, 15(4): 0-0.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] Gao Qingshi; Zhang Xiang; Yang Shufan; Chen Shuqing;. Vector Computer 757[J]. , 1986, 1(3): 1 -14 .
[2] Wu Enhua;. A Graphics System Distributed across a Local Area Network[J]. , 1986, 1(3): 53 -64 .
[3] Chen Zhaoxiong; Gao Qingshi;. A Substitution Based Model for the Implementation of PROLOG——The Design and Implementation of LPROLOG[J]. , 1986, 1(4): 17 -26 .
[4] Zheng Guoliang; Li Hui;. The Design and Implementation of the Syntax-Directed Editor Generator(SEG)[J]. , 1986, 1(4): 39 -48 .
[5] Min Yinghua; Han Zhide;. A Built-in Test Pattern Generator[J]. , 1986, 1(4): 62 -74 .
[6] Min Yinghua;. Easy Test Generation PLAs[J]. , 1987, 2(1): 72 -80 .
[7] Li Minghui;. CAD System of Microprogrammed Digital Systems[J]. , 1987, 2(3): 226 -235 .
[8] Lin Qi; Xia Peisu;. The Design and Implementation of a Very Fast Experimental Pipelining Computer[J]. , 1988, 3(1): 1 -6 .
[9] Li Renwei;. Soundness and Completeness of Kung s Reasoning Procedure[J]. , 1988, 3(1): 7 -15 .
[10] Bao Feng;. On the Condition for FSM Being a Scrambler[J]. , 1988, 3(1): 70 -74 .

ISSN 1000-9000(Print)

         1860-4749(Online)
CN 11-2296/TP

Home
Editorial Board
Author Guidelines
Subscription
Journal of Computer Science and Technology
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
Tel.:86-10-62610746
E-mail: jcst@ict.ac.cn
 
  Copyright ©2015 JCST, All Rights Reserved