On Which Nodes Does GCN Fail? Enhancing GCN From the Node Perspective

Jincheng Huang, Jialie Shen, Xiaoshuang Shi, Xiaofeng Zhu
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:20073-20095, 2024.

Abstract

The label smoothness assumption is at the core of Graph Convolutional Networks (GCNs): nodes in a local region have similar labels. Thus, GCN performs local feature smoothing operation to adhere to this assumption. However, there exist some nodes whose labels obtained by feature smoothing conflict with the label smoothness assumption. We find that the label smoothness assumption and the process of feature smoothing are both problematic on these nodes, and call these nodes out of GCN’s control (OOC nodes). In this paper, first, we design the corresponding algorithm to locate the OOC nodes, then we summarize the characteristics of OOC nodes that affect their representation learning, and based on their characteristics, we present DaGCN, an efficient framework that can facilitate the OOC nodes. Extensive experiments verify the superiority of the proposed method and demonstrate that current advanced GCNs are improvements specifically on OOC nodes; the remaining nodes under GCN’s control (UC nodes) are already optimally represented by vanilla GCN on most datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-huang24t, title = {On Which Nodes Does {GCN} Fail? {E}nhancing {GCN} From the Node Perspective}, author = {Huang, Jincheng and Shen, Jialie and Shi, Xiaoshuang and Zhu, Xiaofeng}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {20073--20095}, year = {2024}, editor = {Salakhutdinov, Ruslan and Kolter, Zico and Heller, Katherine and Weller, Adrian and Oliver, Nuria and Scarlett, Jonathan and Berkenkamp, Felix}, volume = {235}, series = {Proceedings of Machine Learning Research}, month = {21--27 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v235/main/assets/huang24t/huang24t.pdf}, url = {https://proceedings.mlr.press/v235/huang24t.html}, abstract = {The label smoothness assumption is at the core of Graph Convolutional Networks (GCNs): nodes in a local region have similar labels. Thus, GCN performs local feature smoothing operation to adhere to this assumption. However, there exist some nodes whose labels obtained by feature smoothing conflict with the label smoothness assumption. We find that the label smoothness assumption and the process of feature smoothing are both problematic on these nodes, and call these nodes out of GCN’s control (OOC nodes). In this paper, first, we design the corresponding algorithm to locate the OOC nodes, then we summarize the characteristics of OOC nodes that affect their representation learning, and based on their characteristics, we present DaGCN, an efficient framework that can facilitate the OOC nodes. Extensive experiments verify the superiority of the proposed method and demonstrate that current advanced GCNs are improvements specifically on OOC nodes; the remaining nodes under GCN’s control (UC nodes) are already optimally represented by vanilla GCN on most datasets.} }
Endnote
%0 Conference Paper %T On Which Nodes Does GCN Fail? Enhancing GCN From the Node Perspective %A Jincheng Huang %A Jialie Shen %A Xiaoshuang Shi %A Xiaofeng Zhu %B Proceedings of the 41st International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2024 %E Ruslan Salakhutdinov %E Zico Kolter %E Katherine Heller %E Adrian Weller %E Nuria Oliver %E Jonathan Scarlett %E Felix Berkenkamp %F pmlr-v235-huang24t %I PMLR %P 20073--20095 %U https://proceedings.mlr.press/v235/huang24t.html %V 235 %X The label smoothness assumption is at the core of Graph Convolutional Networks (GCNs): nodes in a local region have similar labels. Thus, GCN performs local feature smoothing operation to adhere to this assumption. However, there exist some nodes whose labels obtained by feature smoothing conflict with the label smoothness assumption. We find that the label smoothness assumption and the process of feature smoothing are both problematic on these nodes, and call these nodes out of GCN’s control (OOC nodes). In this paper, first, we design the corresponding algorithm to locate the OOC nodes, then we summarize the characteristics of OOC nodes that affect their representation learning, and based on their characteristics, we present DaGCN, an efficient framework that can facilitate the OOC nodes. Extensive experiments verify the superiority of the proposed method and demonstrate that current advanced GCNs are improvements specifically on OOC nodes; the remaining nodes under GCN’s control (UC nodes) are already optimally represented by vanilla GCN on most datasets.
APA
Huang, J., Shen, J., Shi, X. & Zhu, X.. (2024). On Which Nodes Does GCN Fail? Enhancing GCN From the Node Perspective. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:20073-20095 Available from https://proceedings.mlr.press/v235/huang24t.html.

Related Material