Alternately Optimized Graph Neural Networks

Haoyu Han, Xiaorui Liu, Haitao Mao, Mohamadali Torkamani, Feng Shi, Victor Lee, Jiliang Tang
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:12411-12429, 2023.

Abstract

Graph Neural Networks (GNNs) have greatly advanced the semi-supervised node classification task on graphs. The majority of existing GNNs are trained in an end-to-end manner that can be viewed as tackling a bi-level optimization problem. This process is often inefficient in computation and memory usage. In this work, we propose a new optimization framework for semi-supervised learning on graphs from a multi-view learning perspective. The proposed framework can be conveniently solved by the alternating optimization algorithms, resulting in significantly improved efficiency. Extensive experiments demonstrate that the proposed method can achieve comparable or better performance with state-of-the-art baselines while it has significantly better computation and memory efficiency.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-han23c, title = {Alternately Optimized Graph Neural Networks}, author = {Han, Haoyu and Liu, Xiaorui and Mao, Haitao and Torkamani, Mohamadali and Shi, Feng and Lee, Victor and Tang, Jiliang}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {12411--12429}, 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/han23c/han23c.pdf}, url = {https://proceedings.mlr.press/v202/han23c.html}, abstract = {Graph Neural Networks (GNNs) have greatly advanced the semi-supervised node classification task on graphs. The majority of existing GNNs are trained in an end-to-end manner that can be viewed as tackling a bi-level optimization problem. This process is often inefficient in computation and memory usage. In this work, we propose a new optimization framework for semi-supervised learning on graphs from a multi-view learning perspective. The proposed framework can be conveniently solved by the alternating optimization algorithms, resulting in significantly improved efficiency. Extensive experiments demonstrate that the proposed method can achieve comparable or better performance with state-of-the-art baselines while it has significantly better computation and memory efficiency.} }
Endnote
%0 Conference Paper %T Alternately Optimized Graph Neural Networks %A Haoyu Han %A Xiaorui Liu %A Haitao Mao %A Mohamadali Torkamani %A Feng Shi %A Victor Lee %A Jiliang Tang %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-han23c %I PMLR %P 12411--12429 %U https://proceedings.mlr.press/v202/han23c.html %V 202 %X Graph Neural Networks (GNNs) have greatly advanced the semi-supervised node classification task on graphs. The majority of existing GNNs are trained in an end-to-end manner that can be viewed as tackling a bi-level optimization problem. This process is often inefficient in computation and memory usage. In this work, we propose a new optimization framework for semi-supervised learning on graphs from a multi-view learning perspective. The proposed framework can be conveniently solved by the alternating optimization algorithms, resulting in significantly improved efficiency. Extensive experiments demonstrate that the proposed method can achieve comparable or better performance with state-of-the-art baselines while it has significantly better computation and memory efficiency.
APA
Han, H., Liu, X., Mao, H., Torkamani, M., Shi, F., Lee, V. & Tang, J.. (2023). Alternately Optimized Graph Neural Networks. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:12411-12429 Available from https://proceedings.mlr.press/v202/han23c.html.

Related Material