Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks

Jincheng Huang, Yujie Mo, Xiaoshuang Shi, Lei Feng, Xiaofeng Zhu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:25613-25633, 2025.

Abstract

The message-passing mechanism of graph convolutional networks (i.e., GCNs) enables label information to reach more unlabeled neighbors, thereby increasing the utilization of labels. However, the additional label information does not always contribute positively to the GCN. To address this issue, we propose a new two-step framework called ELU-GCN. In the first stage, ELU-GCN conducts graph learning to learn a new graph structure (i.e., ELU-graph), which allows the additional label information to positively influence the predictions of GCN. In the second stage, we design a new graph contrastive learning on the GCN framework for representation learning by exploring the consistency and mutually exclusive information between the learned ELU graph and the original graph. Moreover, we theoretically demonstrate that the proposed method can ensure the generalization ability of GCNs. Extensive experiments validate the superiority of our method.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-huang25x, title = {Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks}, author = {Huang, Jincheng and Mo, Yujie and Shi, Xiaoshuang and Feng, Lei and Zhu, Xiaofeng}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {25613--25633}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/huang25x/huang25x.pdf}, url = {https://proceedings.mlr.press/v267/huang25x.html}, abstract = {The message-passing mechanism of graph convolutional networks (i.e., GCNs) enables label information to reach more unlabeled neighbors, thereby increasing the utilization of labels. However, the additional label information does not always contribute positively to the GCN. To address this issue, we propose a new two-step framework called ELU-GCN. In the first stage, ELU-GCN conducts graph learning to learn a new graph structure (i.e., ELU-graph), which allows the additional label information to positively influence the predictions of GCN. In the second stage, we design a new graph contrastive learning on the GCN framework for representation learning by exploring the consistency and mutually exclusive information between the learned ELU graph and the original graph. Moreover, we theoretically demonstrate that the proposed method can ensure the generalization ability of GCNs. Extensive experiments validate the superiority of our method.} }
Endnote
%0 Conference Paper %T Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks %A Jincheng Huang %A Yujie Mo %A Xiaoshuang Shi %A Lei Feng %A Xiaofeng Zhu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-huang25x %I PMLR %P 25613--25633 %U https://proceedings.mlr.press/v267/huang25x.html %V 267 %X The message-passing mechanism of graph convolutional networks (i.e., GCNs) enables label information to reach more unlabeled neighbors, thereby increasing the utilization of labels. However, the additional label information does not always contribute positively to the GCN. To address this issue, we propose a new two-step framework called ELU-GCN. In the first stage, ELU-GCN conducts graph learning to learn a new graph structure (i.e., ELU-graph), which allows the additional label information to positively influence the predictions of GCN. In the second stage, we design a new graph contrastive learning on the GCN framework for representation learning by exploring the consistency and mutually exclusive information between the learned ELU graph and the original graph. Moreover, we theoretically demonstrate that the proposed method can ensure the generalization ability of GCNs. Extensive experiments validate the superiority of our method.
APA
Huang, J., Mo, Y., Shi, X., Feng, L. & Zhu, X.. (2025). Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:25613-25633 Available from https://proceedings.mlr.press/v267/huang25x.html.

Related Material