Progressive Label Disambiguation for Partial Label Learning in Homogeneous Graphs
Pages 3969 - 3973
Abstract
Many existing Graph Neural Networks (GNN) methods assume that labels are reliable and sufficient, which may not be the case in real-world scenarios. This paper addresses one such problem of Partial Label Learning (PLL) on graph-structured data. In the PLL for graphs, each node is represented by a candidate set of labels, where only one is true while the others are inaccurate. Despite advancements with PLL in tabular and vision domains, the graph-structured data still needs to be explored. In this work, we first define PLL for graphs. Subsequently, we propose a new PLD-Graph algorithm for PLL in homogeneous graphs with scarce labels. We utilize graph augmentation to reduce the effects of inexact labels and provide additional supervision from unlabeled nodes. Progressive label disambiguation is performed based on the model's ability to predict correct classes. Furthermore, an additional loss estimates the label corruption matrix to capture associations between correct and incorrect labels. We show the effectiveness of the proposed algorithm on multiple graph datasets, with two types of noise and varying levels of ambiguous labels. Overall, the proposed PLD-Graph algorithm outperforms state-of-the-art PLL methods.
References
[1]
Bruno Klaus Aquino Afonso and Lilian Berton. 2020. Analysis of label noise in graph-based semi-supervised learning. In ACM Symposium on Applied Computing. 1127--1134.
[2]
Zhe Chen, Yuehan Wang, Bin Zhao, Jing Cheng, Xin Zhao, and Zongtao Duan. 2020. Knowledge graph completion: A review. IEEE Access, Vol. 8 (2020), 192435--192456.
[3]
Luca Cosmo, Anees Kazi, Seyed-Ahmad Ahmadi, Nassir Navab, and Michael Bronstein. 2020. Latent-graph learning for disease prediction. In MICCAI. 643--653.
[4]
Enyan Dai, Charu Aggarwal, and Suhang Wang. 2021. NRGNN: Learning a label noise resistant graph neural network on sparsely and noisily labeled graphs. In ACM SIGKDD. 227--236.
[5]
Jinfu Fan, Yang Yu, Linqing Huang, and Zhongjie Wang. 2023. GraphDPI: Partial label disambiguation by graph representation learning via mutual information maximization. Pattern Recognition, Vol. 134 (2023), 109133.
[6]
Bahare Fatemi, Layla El Asri, and Seyed Mehran Kazemi. 2021. SLAPS: Self-supervision improves structure learning for graph neural networks. NeurIPS, Vol. 34 (2021), 22667--22681.
[7]
Eyke Hüllermeier and Jürgen Beringer. 2005. Learning from ambiguously labeled examples. In Intelligent Data Analysis. Springer, 168--179.
[8]
Jiaqi Lv, Miao Xu, Lei Feng, Gang Niu, Xin Geng, and Masashi Sugiyama. 2020. Progressive identification of true labels for partial-label learning. In ICLR. 6500--6510.
[9]
Gengyu Lyu, Songhe Feng, Shaokai Wang, and Zhen Yang. 2023. Prior Knowledge Constrained Adaptive Graph Framework for Partial Label Learning. ACM Transactions on IST, Vol. 14, 2 (2023), 1--16.
[10]
Gengyu Lyu, Songhe Feng, Tao Wang, Congyan Lang, and Yidong Li. 2019. GM-PLL: Graph matching based partial label learning. IEEE Transactions on KDE, Vol. 33, 2 (2019), 521--535.
[11]
Gengyu Lyu, Yanan Wu, and Songhe Feng. 2022. Deep graph matching for partial label learning. In IJCAI. 3306--3312.
[12]
Eran Malach and Shai Shalev-Shwartz. 2017. Decoupling" when to update" from" how to update". NeurIPS, Vol. 30 (2017).
[13]
Andrew Kachites McCallum, Kamal Nigam, Jason Rennie, and Kristie Seymore. 2000. Automating the construction of internet portals with machine learning. Information Retrieval, Vol. 3 (2000), 127--163.
[14]
Miller McPherson, Lynn Smith-Lovin, and James M Cook. 2001. Birds of a feather: Homophily in social networks. Annual review of sociology, Vol. 27, 1 (2001), 415--444.
[15]
Péter Mernyei and Cuatualina Cangea. 2020. Wiki-cs: A wikipedia-based benchmark for graph neural networks. arXiv preprint arXiv:2007.02901 (2020).
[16]
Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. NeurIPS, Vol. 26 (2013).
[17]
Siyi Qian, Haochao Ying, Renjun Hu, Jingbo Zhou, Jintai Chen, Danny Z Chen, and Jian Wu. 2023. Robust Training of Graph Neural Networks via Noise Governance. In WSDM. 607--615.
[18]
Yingjie Tian, Xiaotong Yu, and Saiji Fu. 2023. Partial label learning: Taxonomy, analysis and outlook. Neural Networks (2023).
[19]
Haobo Wang, Mingxuan Xia, Yixuan Li, Yuren Mao, Lei Feng, Gang Chen, and Junbo Zhao. 2022. SoLar: Sinkhorn Label Refinery for Imbalanced Partial-Label Learning. arXiv preprint:2209.10365 (2022).
[20]
Haobo Wang, Ruixuan Xiao, Yixuan Li, Lei Feng, Gang Niu, Gang Chen, and Junbo Zhao. 2022. Pico: Contrastive label disambiguation for partial label learning. In ICLR.
[21]
Hongwei Wen, Jingyi Cui, Hanyuan Hang, Jiabin Liu, Yisen Wang, and Zhouchen Lin. 2021. Leveraged weighted loss for partial label learning. In ICML. 11091--11100.
[22]
Dong-Dong Wu, Deng-Bao Wang, and Min-Ling Zhang. 2022. Revisiting consistency regularization for deep partial label learning. In ICLR. 24212--24225.
[23]
Zonghan Wu, Shirui Pan, Fengwen Chen, Guodong Long, Chengqi Zhang, and S Yu Philip. 2020. A comprehensive survey on graph neural networks. IEEE transactions on NNLS, Vol. 32, 1 (2020), 4--24.
[24]
S Xia, Jiaqi Lv, Ning Xu, and Xin Geng. 2022. Ambiguity-induced contrastive learning for instance-dependent partial label learning. In IJCAI. 3615--3621.
[25]
Yan Yan and Yuhong Guo. 2023. Mutual Partial Label Learning with Competitive Label Noise. In ICLR.
[26]
Fei Zhang, Lei Feng, Bo Han, Tongliang Liu, Gang Niu, Tao Qin, and Masashi Sugiyama. 2022. Exploiting class activation value for partial-label learning. In ICLR.
[27]
Zhi-Hua Zhou. 2018. A brief introduction to weakly supervised learning. National science review, Vol. 5, 1 (2018), 44--53.
Index Terms
- Progressive Label Disambiguation for Partial Label Learning in Homogeneous Graphs
Recommendations
Noisy Label Removal for Partial Multi-Label Learning
KDD '24: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data MiningThis paper addresses the problem of partial multi-label learning (PML), a challenging weakly supervised learning framework, where each sample is associated with a candidate label set comprising both ground-true labels and noisy labels. We theoretically ...
Semi-supervised partial label learning algorithm via reliable label propagation
AbstractPartial label learning (PLL) is a weakly supervised learning method that is able to predict one label as the correct answer from a given candidate label set. In PLL, when all possible candidate labels are as signed to real-world training examples, ...
Maximum margin partial label learning
Partial label learning aims to learn from training examples each associated with a set of candidate labels, among which only one label is valid for the training example. The basic strategy to learn from partial label examples is disambiguation, i.e. by ...
Comments
Information & Contributors
Information
Published In
October 2024
5705 pages
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 21 October 2024
Check for updates
Author Tags
Qualifiers
- Short-paper
Conference
CIKM '24
Sponsor:
CIKM '24: The 33rd ACM International Conference on Information and Knowledge Management
October 21 - 25, 2024
ID, Boise, USA
Acceptance Rates
Overall Acceptance Rate 1,861 of 8,427 submissions, 22%
Upcoming Conference
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 61Total Downloads
- Downloads (Last 12 months)61
- Downloads (Last 6 weeks)31
Reflects downloads up to 24 Dec 2024
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in