Graph Adversarial Diffusion Convolution

Songtao Liu, Jinghui Chen, Tianfan Fu, Lu Lin, Marinka Zitnik, Dinghao Wu
Proceedings of the 41st International Conference on Machine Learning, PMLR 235:30789-30806, 2024.

Abstract

This paper introduces a min-max optimization formulation for the Graph Signal Denoising (GSD) problem. In this formulation, we first maximize the second term of GSD by introducing perturbations to the graph structure based on Laplacian distance and then minimize the overall loss of the GSD. By solving the min-max optimization problem, we derive a new variant of the Graph Diffusion Convolution (GDC) architecture, called Graph Adversarial Diffusion Convolution (GADC). GADC differs from GDC by incorporating an additional term that enhances robustness against adversarial attacks on the graph structure and noise in node features. Moreover, GADC improves the performance of GDC on heterophilic graphs. Extensive experiments demonstrate the effectiveness of GADC across various datasets. Code is available at https://github.com/SongtaoLiu0823/GADC.

Cite this Paper

BibTeX
@InProceedings{pmlr-v235-liu24h, title = {Graph Adversarial Diffusion Convolution}, author = {Liu, Songtao and Chen, Jinghui and Fu, Tianfan and Lin, Lu and Zitnik, Marinka and Wu, Dinghao}, booktitle = {Proceedings of the 41st International Conference on Machine Learning}, pages = {30789--30806}, 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/liu24h/liu24h.pdf}, url = {https://proceedings.mlr.press/v235/liu24h.html}, abstract = {This paper introduces a min-max optimization formulation for the Graph Signal Denoising (GSD) problem. In this formulation, we first maximize the second term of GSD by introducing perturbations to the graph structure based on Laplacian distance and then minimize the overall loss of the GSD. By solving the min-max optimization problem, we derive a new variant of the Graph Diffusion Convolution (GDC) architecture, called Graph Adversarial Diffusion Convolution (GADC). GADC differs from GDC by incorporating an additional term that enhances robustness against adversarial attacks on the graph structure and noise in node features. Moreover, GADC improves the performance of GDC on heterophilic graphs. Extensive experiments demonstrate the effectiveness of GADC across various datasets. Code is available at https://github.com/SongtaoLiu0823/GADC.} }
Endnote
%0 Conference Paper %T Graph Adversarial Diffusion Convolution %A Songtao Liu %A Jinghui Chen %A Tianfan Fu %A Lu Lin %A Marinka Zitnik %A Dinghao Wu %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-liu24h %I PMLR %P 30789--30806 %U https://proceedings.mlr.press/v235/liu24h.html %V 235 %X This paper introduces a min-max optimization formulation for the Graph Signal Denoising (GSD) problem. In this formulation, we first maximize the second term of GSD by introducing perturbations to the graph structure based on Laplacian distance and then minimize the overall loss of the GSD. By solving the min-max optimization problem, we derive a new variant of the Graph Diffusion Convolution (GDC) architecture, called Graph Adversarial Diffusion Convolution (GADC). GADC differs from GDC by incorporating an additional term that enhances robustness against adversarial attacks on the graph structure and noise in node features. Moreover, GADC improves the performance of GDC on heterophilic graphs. Extensive experiments demonstrate the effectiveness of GADC across various datasets. Code is available at https://github.com/SongtaoLiu0823/GADC.
APA
Liu, S., Chen, J., Fu, T., Lin, L., Zitnik, M. & Wu, D.. (2024). Graph Adversarial Diffusion Convolution. Proceedings of the 41st International Conference on Machine Learning, in Proceedings of Machine Learning Research 235:30789-30806 Available from https://proceedings.mlr.press/v235/liu24h.html.

Related Material