Disentangled Multiplex Graph Representation Learning

Yujie Mo, Yajie Lei, Jialie Shen, Xiaoshuang Shi, Heng Tao Shen, Xiaofeng Zhu
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:24983-25005, 2023.

Abstract

Unsupervised multiplex graph representation learning (UMGRL) has received increasing interest, but few works simultaneously focused on the common and private information extraction. In this paper, we argue that it is essential for conducting effective and robust UMGRL to extract complete and clean common information, as well as more-complementarity and less-noise private information. To achieve this, we first investigate disentangled representation learning for the multiplex graph to capture complete and clean common information, as well as design a contrastive constraint to preserve the complementarity and remove the noise in the private information. Moreover, we theoretically analyze that the common and private representations learned by our method are provably disentangled and contain more task-relevant and less task-irrelevant information to benefit downstream tasks. Extensive experiments verify the superiority of the proposed method in terms of different downstream tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-mo23a, title = {Disentangled Multiplex Graph Representation Learning}, author = {Mo, Yujie and Lei, Yajie and Shen, Jialie and Shi, Xiaoshuang and Shen, Heng Tao and Zhu, Xiaofeng}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {24983--25005}, 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/mo23a/mo23a.pdf}, url = {https://proceedings.mlr.press/v202/mo23a.html}, abstract = {Unsupervised multiplex graph representation learning (UMGRL) has received increasing interest, but few works simultaneously focused on the common and private information extraction. In this paper, we argue that it is essential for conducting effective and robust UMGRL to extract complete and clean common information, as well as more-complementarity and less-noise private information. To achieve this, we first investigate disentangled representation learning for the multiplex graph to capture complete and clean common information, as well as design a contrastive constraint to preserve the complementarity and remove the noise in the private information. Moreover, we theoretically analyze that the common and private representations learned by our method are provably disentangled and contain more task-relevant and less task-irrelevant information to benefit downstream tasks. Extensive experiments verify the superiority of the proposed method in terms of different downstream tasks.} }
Endnote
%0 Conference Paper %T Disentangled Multiplex Graph Representation Learning %A Yujie Mo %A Yajie Lei %A Jialie Shen %A Xiaoshuang Shi %A Heng Tao Shen %A Xiaofeng Zhu %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-mo23a %I PMLR %P 24983--25005 %U https://proceedings.mlr.press/v202/mo23a.html %V 202 %X Unsupervised multiplex graph representation learning (UMGRL) has received increasing interest, but few works simultaneously focused on the common and private information extraction. In this paper, we argue that it is essential for conducting effective and robust UMGRL to extract complete and clean common information, as well as more-complementarity and less-noise private information. To achieve this, we first investigate disentangled representation learning for the multiplex graph to capture complete and clean common information, as well as design a contrastive constraint to preserve the complementarity and remove the noise in the private information. Moreover, we theoretically analyze that the common and private representations learned by our method are provably disentangled and contain more task-relevant and less task-irrelevant information to benefit downstream tasks. Extensive experiments verify the superiority of the proposed method in terms of different downstream tasks.
APA
Mo, Y., Lei, Y., Shen, J., Shi, X., Shen, H.T. & Zhu, X.. (2023). Disentangled Multiplex Graph Representation Learning. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:24983-25005 Available from https://proceedings.mlr.press/v202/mo23a.html.

Related Material