All in a Row: Compressed Convolution Networks for Graphs

Junshu Sun, Shuhui Wang, Xinzhe Han, Zhe Xue, Qingming Huang
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:33061-33076, 2023.

Abstract

Compared to Euclidean convolution, existing graph convolution methods generally fail to learn diverse convolution operators under limited parameter scales and depend on additional treatments of multi-scale feature extraction. The challenges of generalizing Euclidean convolution to graphs arise from the irregular structure of graphs. To bridge the gap between Euclidean space and graph space, we propose a differentiable method for regularization on graphs that applies permutations to the input graphs. The permutations constrain all nodes in a row regardless of their input order and therefore enable the flexible generalization of Euclidean convolution. Based on the regularization of graphs, we propose Compressed Convolution Network (CoCN) for hierarchical graph representation learning. CoCN follows the local feature learning and global parameter sharing mechanisms of Convolution Neural Networks. The whole model can be trained end-to-end and is able to learn both individual node features and the corresponding structure features. We validate CoCN on several node classification and graph classification benchmarks. CoCN achieves superior performance over competitive convolutional GNNs and graph pooling models. Codes are available at https://github.com/sunjss/CoCN.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-sun23k, title = {All in a Row: Compressed Convolution Networks for Graphs}, author = {Sun, Junshu and Wang, Shuhui and Han, Xinzhe and Xue, Zhe and Huang, Qingming}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {33061--33076}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/sun23k/sun23k.pdf}, url = {https://proceedings.mlr.press/v202/sun23k.html}, abstract = {Compared to Euclidean convolution, existing graph convolution methods generally fail to learn diverse convolution operators under limited parameter scales and depend on additional treatments of multi-scale feature extraction. The challenges of generalizing Euclidean convolution to graphs arise from the irregular structure of graphs. To bridge the gap between Euclidean space and graph space, we propose a differentiable method for regularization on graphs that applies permutations to the input graphs. The permutations constrain all nodes in a row regardless of their input order and therefore enable the flexible generalization of Euclidean convolution. Based on the regularization of graphs, we propose Compressed Convolution Network (CoCN) for hierarchical graph representation learning. CoCN follows the local feature learning and global parameter sharing mechanisms of Convolution Neural Networks. The whole model can be trained end-to-end and is able to learn both individual node features and the corresponding structure features. We validate CoCN on several node classification and graph classification benchmarks. CoCN achieves superior performance over competitive convolutional GNNs and graph pooling models. Codes are available at https://github.com/sunjss/CoCN.} }
Endnote
%0 Conference Paper %T All in a Row: Compressed Convolution Networks for Graphs %A Junshu Sun %A Shuhui Wang %A Xinzhe Han %A Zhe Xue %A Qingming Huang %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-sun23k %I PMLR %P 33061--33076 %U https://proceedings.mlr.press/v202/sun23k.html %V 202 %X Compared to Euclidean convolution, existing graph convolution methods generally fail to learn diverse convolution operators under limited parameter scales and depend on additional treatments of multi-scale feature extraction. The challenges of generalizing Euclidean convolution to graphs arise from the irregular structure of graphs. To bridge the gap between Euclidean space and graph space, we propose a differentiable method for regularization on graphs that applies permutations to the input graphs. The permutations constrain all nodes in a row regardless of their input order and therefore enable the flexible generalization of Euclidean convolution. Based on the regularization of graphs, we propose Compressed Convolution Network (CoCN) for hierarchical graph representation learning. CoCN follows the local feature learning and global parameter sharing mechanisms of Convolution Neural Networks. The whole model can be trained end-to-end and is able to learn both individual node features and the corresponding structure features. We validate CoCN on several node classification and graph classification benchmarks. CoCN achieves superior performance over competitive convolutional GNNs and graph pooling models. Codes are available at https://github.com/sunjss/CoCN.
APA
Sun, J., Wang, S., Han, X., Xue, Z. & Huang, Q.. (2023). All in a Row: Compressed Convolution Networks for Graphs. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:33061-33076 Available from https://proceedings.mlr.press/v202/sun23k.html.

Related Material