GLDL: graph label distribution learning
AUTHORs: 
Yufei Jin, Richard Gao, Yi He, Xingquan ZhuAuthors Info & Claims
Yufei Jin, Richard Gao, Yi He, Xingquan ZhuAuthors Info & ClaimsArticle No.: 1446, Pages 12965 - 12974
Abstract
Label Distribution Learning (LDL), as a more general learning setting than generic single-label and multi-label learning, has been commonly used in computer vision and many other applications. To date, existing LDL approaches are designed and applied to data without considering the interdependence between instances. In this paper, we propose a Graph Label Distribution Learning (GLDL) framework, which explicitly models three types of relationships: instance-instance, labellabel, and instance-label, to learn the label distribution for networked data. A label-label network is learned to capture label-to-label correlation, through which GLDL can accurately learn label distributions for nodes. Dual graph convolution network (GCN) Co-training with heterogeneous message passing ensures two GCNs, one focusing on instance-instance relationship and the other one targeting label-label correlation, are jointly trained such that instance-instance relationship can help induce label-label correlation and vice versa. Our theoretical study derives the error bound of GLDL. For verification, four benchmark datasets with label distributions for nodes are created using common graph benchmarks. The experiments show that considering dependency helps learn better label distributions for networked data, compared to state-of-the-art LDL baseline. In addition, GLDL not only outperforms simple GCN and graph attention networks (GAT) using distribution loss but is also superior to its variant considering label-label relationship as a static network. GLDL and its benchmarks are the first research endeavors to address LDL for graphs. Code and benchmark data are released for public access.
References
[1]
Bacciu, D.; Errica, F.; Micheli, A.; and Podda, M. 2020. A gentle introduction to deep learning for graphs. Neural Networks, 129: 203-221.
[2]
Borchani, H.; Varando, G.; Bielza, C.; and Larranaga, P. 2015. A survey on multi-output regression. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 5.
[3]
Carbonell, J. G.; Michalski, R. S.; and Mitchell, T. M. 1983. An overview of machine learning. Machine learning, 3-23.
[4]
Chen, S.; Wang, J.; Chen, Y.; Shi, Z.; Geng, X.; and Rui, Y. 2020. Label distribution learning on auxiliary label space graphs for facial expression recognition. In CVPR, 1398-413993.
[5]
Chen, Z.-M.; Wei, X.-S.; Wang, P.; and Guo, Y. 2019. Multilabel image recognition with graph convolutional networks. In CVPR, 5177-5186.
[6]
Fu, X.; Zhang, J.; Meng, Z.; and King, I. 2020. MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding. In WWW, 2331-2341.
[7]
Geng, X. 2016. Label distribution learning. IEEE Transactions on Knowledge and Data Engineering, 28(7): 1734-1748.
[8]
Geng, X.; Yin, C.; and Zhou, Z.-H. 2013. Facial age estimation by learning from label distributions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(10): 2401-2412.
[9]
Hamilton, W. L.; Ying, R.; and Leskovec, J. 2017. Inductive Representation Learning on Large Graphs. In NeurIPS, 1025-1035.
[10]
Jia, X.; Li, W.; Liu, J.; et al. 2018. Label Distribution Learning by Exploiting Label Correlations. In AAAI.
[11]
Jin, W.; Zhao, L.; Zhang, S.; Liu, Y.; Tang, J.; and Shah, N. 2022. Graph Condensation for Graph Neural Networks. In ICLR.
[12]
Kakade, S. M.; Sridharan, K.; and Tewari, A. 2008. On the complexity of linear prediction: Risk bounds, margin bounds, and regularization. NeurIPS, 21.
[13]
Kipf, T. N.; and Welling, M. 2016. Variational Graph AutoEncoders. In Proc. of the NeurIPS Bayesian Deep Learning Workshop.
[14]
Kipf, T. N.; and Welling, M. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In ICLR.
[15]
Kotsiantis, S. B.; Zaharakis, I. D.; and Pintelas, P. E. 2006. Machine learning: a review of classification and combining techniques. Artificial Intelligence Review, 26: 159-190.
[16]
Kou, Z.; Wang, J.; Jia, Y.; and Geng, X. 2023. Exploiting Multi-Label Correlation in Label Distribution Learning. In ArXiv:2308.01742.
[17]
Ma, Y.; Liu, X.; Shah, N.; and Tang, J. 2022. Is Homophily a Necessity for Graph Neural Networks? In ICLR.
[18]
Tang, J.; Zhang, J.; Yao, L.; Li, J.; Zhang, L.; and Su, Z. 2008. ArnetMiner: Extraction and Mining of Academic Social Networks. In KDD, 990-998.
[19]
Veličković, P.; Cucurull, G.; Casanova, A.; Romero, A.; Liò, P.; and Bengio, Y. 2018. Graph Attention Networks. In ICLR.
[20]
Wang, J.; and Geng, X. 2023. Label Distribution Learning by Exploiting Label Distribution Manifold. IEEE Transactions on Neural Networks and Learning Systems, 839-852.
[21]
Xie, X.; Tian, M.; Luo, G.; et al. 2023. Active learning in multi-label image classification with graph convolutional network embedding. Future Generation Computer Systems, 148: 56-65.
[22]
Xu, H.; Liu, X.; Zhao, Q.; Ma, Y.; Yan, C.; and Dai, F. 2023. Gaussian Label Distribution Learning for Spherical Image Object Detection. In CVPR.
[23]
Xu, K.; Hu, W.; Leskovec, J.; and Jegelka, S. 2019. How Powerful are Graph Neural Networks? In ICLR.
[24]
Zhang, M.-L.; Zhang, Q.-W.; Fang, J.-P.; Li, Y.-K.; and Geng, X. 2021. Leveraging Implicit Relative Labeling-Importance Information for Effective Multi-Label Learning. IEEE Transactions on Knowledge and Data Engineering, 33(5): 2057-2070.
[25]
Zhu, J.; Yan, Y.; Zhao, L.; Heimann, M.; Akoglu, L.; and Koutra, D. 2020. Beyond homophily in graph neural networks: Current limitations and effective designs. NeurIPS, 33: 7793-7804.
Index Terms
- GLDL: graph label distribution learning
Index terms have been assigned to the content through auto-classification.
Recommendations
Transductive Multilabel Learning via Label Set Propagation
The problem of multilabel classification has attracted great interest in the last decade, where each instance can be assigned with a set of multiple class labels simultaneously. It has a wide variety of real-world applications, e.g., automatic image ...
Inductive Semi-supervised Multi-Label Learning with Co-Training
KDD '17: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningIn multi-label learning, each training example is associated with multiple class labels and the task is to learn a mapping from the feature space to the power set of label space. It is generally demanding and time-consuming to obtain labels for training ...
Sentiment labeling for extending initial labeled data to improve semi-supervised sentiment classification
Semi-supervised framework which exploits unsupervised approach (JST) is proposed.Self-training suffers from incorrectly labeling problem with insufficient data.Confidently predicted instances are labeled and used as training data by JST.Self-training ...
Comments
Information & Contributors
Information
Published In
February 2024
23861 pages
ISBN:978-1-57735-887-9
Copyright © 2024 Association for the Advancement of Artificial Intelligence.
Sponsors
- Association for the Advancement of Artificial Intelligence
Publisher
AAAI Press
Publication History
Published: 20 February 2024
Qualifiers
- Research-article
- Research
- Refereed limited
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 08 Feb 2025