{"type":"ScholarlyArticle","title":"Deep Graph Matching for Partial Label Learning","authors":[{"name":"Gengyu Lyu","slug":"gengyu-lyu","given":"Gengyu","family":"Lyu","affiliation":"School of Computer and Information Technology , Beijing Jiaotong University"},{"name":"Yanan Wu","slug":"yanan-wu","given":"Yanan","family":"Wu","affiliation":"School of Computer and Information Technology , Beijing Jiaotong University"},{"name":"Songhe Feng","slug":"songhe-feng","given":"Songhe","family":"Feng","affiliation":"School of Computer and Information Technology , Beijing Jiaotong University"}],"abstract":"Partial Label Learning (PLL) aims to learn from training data where each instance is associated with a set of candidate labels, among which only one is correct. In this paper, we formulate the task of PLL problem as an ``instance-label'' matching selection problem, and propose a DeepGNN-based graph matching PLL approach to solve it. Specifically, we first construct all instances and labels as graph nodes into two different graphs respectively, and then integrate them into a unified matching graph by connecting each instance to its candidate labels. Afterwards, the graph attention mechanism is adopted to aggregate and update all nodes state on the instance graph to form structural representations for each instance. Finally, each candidate label is embedded into its corresponding instance and derives a matching affinity score for each instance-label correspondence with a progressive cross-entropy loss. Extensive experiments on various data sets have demonstrated the superiority of our proposed method.","doi":"10.24963/ijcai.2022/459","url":"https://ijcai.org/proceedings/2022/459","pdf":"https://ijcai.org/proceedings/2022/0459.pdf","markdown":"https://ijcai.org/proceedings/2022/459.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/459","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Machine Learning","track":"Main Track","number":459,"pages":{"first":3306,"last":3312},"keywords":["Machine Learning: Multi-label"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986498","length_sec":55,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984641","length_sec":352,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Chen et al., 2017] C. Chen, V. Patel, and R. Chellappa. Learning from ambiguously labeled face images. IEEE Transactions on Pattern Analysis and Machine Intelli- gence, 40(7):1653-1667, 2017.","title":"Learning from ambiguously labeled face images","authors":"C Chen, V Patel, R Chellappa","year":"2017","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Cour et al., 2009] T. Cour, B. Sapp, C. Jordan, and B. Taskar. Learning from ambiguously labeled images. In IEEE Conference on Computer Vision and Pattern Recog- nition, pages 919-926, 2009.","title":"Learning from ambiguously labeled images","authors":"T Cour, B Sapp, C Jordan, B Taskar","year":"2009","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Cour et al., 2011] T. Cour, B. Sapp, and B. Taskar. Learn- ing from partial labels. Journal of Machine Learning Re- search, 12(5):1501-1536, 2011.","title":"Learning from partial labels","authors":"T Cour, B Sapp, B Taskar","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Feng and An, 2018] L. Feng and B. An. Leveraging latent label distributions for partial label learning. In Interna- tional Joint Conference on Artificial Intelligence, pages 2107-2113, 2018.","title":"Leveraging latent label distributions for partial label learning","authors":"L Feng, B An","year":"2018","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/291"},{"position":5,"raw":"[Feng and An, 2019] L. Feng and B. An. Partial label learn- ing by semantic difference maximization. In International Joint Conference on Artificial Intelligence, pages 2294- 2300, 2019.","title":"Partial label learning by semantic difference maximization","authors":"L Feng, B An","year":"2019","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2019/318"},{"position":6,"raw":"[Hullermeier and Beringer, 2005] E. Hullermeier and J. Beringer. Learning from ambiguously labeled ex- amples. International Symposium on Intelligent Data Analysis, 10(5):168-179, 2005.","title":"Learning from ambiguously labeled examples","authors":"E Hullermeier, J Beringer","year":"2005","venue":"International Symposium on Intelligent Data Analysis","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Jin and Ghahramani, 2003] R. Jin and Z. Ghahramani. Learning with multiple labels. In Advances in Neural In- formation Processing Systems, pages 921-928, 2003.","title":"Learning with multiple labels","authors":"R Jin, Z Ghahramani","year":"2003","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Liu and Dietterich, 2012] L. Liu and T. Dietterich. A condi- tional multinomial mixture model for superset label learn- ing. In Advances in Neural Information Processing Sys- tems, pages 548-556, 2012.","title":"A conditional multinomial mixture model for superset label learning","authors":"L Liu, T Dietterich","year":"2012","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Liu et al., 2018] S. Liu, C. Chen, Y. Lu, F. Ouyang, and B. Wang. An interactive method to improve crowdsourced annotations. IEEE Transactions on Visualization and Computer Graphics, 25(1):235-245, 2018.","title":"An interactive method to improve crowdsourced annotations","authors":"S Liu, C Chen, Y Lu, F Ouyang, B Wang","year":"2018","venue":"IEEE Transactions on Visualization and Computer Graphics","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Luo and Orabona, 2010] J. Luo and F. Orabona. Learning from candidate labeling sets. In Advances in Neural Infor- mation Processing Systems, pages 1504-1512, 2010.","title":"Learning from candidate labeling sets","authors":"J Luo, F Orabona","year":"2010","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lv et al., 2020] J. Lv, M. Xu, L. Feng, G. Niu, X. Geng, and M. Sugiyama. Progressive identification of true labels for partial-label learning. In International Conference on Machine Learning, pages 6500-6510, 2020.","title":"Progressive identification of true labels for partial-label learning","authors":"J Lv, M Xu, L Feng, G Niu, X Geng, M Sugiyama","year":"2020","venue":"International Conference on Machine Learning","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Lyu et al., 2020a] G. Lyu, S. Feng, Y. Li, Y. Jin, G. Dai, and C. Lang. Hera: Partial label learning by combining het- erogeneous loss with sparse and low-rank regularization. ACM Transactions on Intelligent Systems and Technology, 11(3), 2020.","title":"Hera: Partial label learning by combining heterogeneous loss with sparse and low-rank regularization","authors":"Lyu","year":"2020","venue":"ACM Transactions on Intelligent Systems and Technology","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Lyu et al., 2020b] G. Lyu, S. Feng, T. Wang, and C. Lang. A self-paced regularization framework for partial-label learning. IEEE Transactions on Cybernetics, pages 1-13, 2020.","title":"A self-paced regularization framework for partial-label learning","authors":"Lyu","year":"2020","venue":"IEEE Transactions on Cybernetics","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Lyu et al., 2021] G. Lyu, S. Feng, T. Wang, C. Lang, and Y. Li. Gm-pll: graph matching based partial label learning. IEEE Transactions on Knowledge and Data Engineering, 33:521-535, 2021.","title":"Gm-pll: graph matching based partial label learning","authors":"G Lyu, S Feng, T Wang, C Lang, Y Li","year":"2021","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Vaswani et al., 2017] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. Gomez, L. Kaiser, and I. Polo- sukhin. Attention is all you need. arXiv preprint arXiv:1706.03762, 2017.","title":"Attention is all you need","authors":"A Vaswani, N Shazeer, N Parmar, J Uszkoreit, L Jones, A Gomez, L Kaiser, I Polosukhin","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Veličković et al., 2018] P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio. Graph attention networks. International Conference on Learning Representations, 2018.","title":"Graph attention networks","authors":"P Veličković, G Cucurull, A Casanova, A Romero, P Lio, Y Bengio","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Wang et al., 2019a] D. Wang, L. Li, and M. Zhang. Adap- tive graph guided disambiguation for partial label learning. In ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 83-91, 2019.","title":"Adaptive graph guided disambiguation for partial label learning","authors":"Wang","year":"2019","venue":"ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Wang et al., 2019b] Q. Wang, Y. Li, and Z. Zhou. Partial label learning with unlabeled data. In International Joint Conference on Artificial Intelligence, pages 3755-3761, 2019.","title":"Partial label learning with unlabeled data","authors":"Wang","year":"2019","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2019/521"},{"position":19,"raw":"[Wang et al., 2020] H. Wang, W. Liu, Y. Zhao, T. Hu, K. Chen, and G. Chen. Learning from multi-dimensional partial labels. In International Joint Conference on Artifi- cial Intelligence, pages 2943-2949, 2020.","title":"Learning from multi-dimensional partial labels","authors":"H Wang, W Liu, Y Zhao, T Hu, K Chen, G Chen","year":"2020","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2020/407"},{"position":20,"raw":"[Wang et al., 2022] H. Wang, R. Xiao, S. Li, L. Feng, G. Niu, G.n Chen, and J. Zhao. PiCO: Contrastive label disambiguation for partial label learning. In International Conference on Learning Representations, 2022.","title":"PiCO: Contrastive label disambiguation for partial label learning","authors":"H Wang, R Xiao, S Li, L Feng, G Niu, G Chen, J Zhao","year":"2022","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wu and Zhang, 2018] X. Wu and M. Zhang. Towards en- abling binary decomposition for partial label learning. In International Joint Conference on Artificial Intelligence, pages 2868-2874, 2018.","title":"Towards enabling binary decomposition for partial label learning","authors":"Zhang Wu, X Wu, M Zhang","year":"2018","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2018/398"},{"position":22,"raw":"[Yu and Zhang, 2016] F. Yu and M. Zhang. Maximum mar- gin partial label learning. Machine Learning, 4(106):573- 593, 2016.","title":"Maximum margin partial label learning","authors":"F Yu, M Zhang","year":"2016","venue":"Machine Learning","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zeng et al., 2013] Z. Zeng, S. Xiao, K. Jia, T. Chan, S. Gao, D. Xu, and Y. Ma. Learning by associating ambiguously labeled images. In IEEE Conference on Computer Vision and Pattern Recognition, pages 708-715, 2013.","title":"Learning by associating ambiguously labeled images","authors":"Z Zeng, S Xiao, K Jia, T Chan, S Gao, D Xu, Y Ma","year":"2013","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhang and Yu, 2015] M. Zhang and F. Yu. Solving the par- tial label learning problem: an instance-based approach. In International Joint Conference on Artificial Intelligence, pages 4048-4054, 2015.","title":"Solving the partial label learning problem: an instance-based approach","authors":"M Zhang, F Yu","year":"2015","venue":"International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2015/568"},{"position":25,"raw":"[Zhang et al., 2017] M. Zhang, F. Yu, and C. Tang. Disambiguation-free partial label learning. IEEE Transac- tions on Knowledge and Data Engineering, 29(10):2155- 2167, 2017.","title":"Disambiguation-free partial label learning","authors":"M Zhang, F Yu, C Tang","year":"2017","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}