Link Prediction with Persistent Homology: An Interactive View

Zuoyu Yan, Tengfei Ma, Liangcai Gao, Zhi Tang, Chao Chen
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11659-11669, 2021.

Abstract

Link prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our topological feature, based on the extended persistent homology, encodes rich structural information regarding the multi-hop paths connecting nodes. Based on this feature, we propose a graph neural network method that outperforms state-of-the-arts on different benchmarks. As another contribution, we propose a novel algorithm to more efficiently compute the extended persistence diagrams for graphs. This algorithm can be generally applied to accelerate many other topological methods for graph learning tasks.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-yan21b, title = {Link Prediction with Persistent Homology: An Interactive View}, author = {Yan, Zuoyu and Ma, Tengfei and Gao, Liangcai and Tang, Zhi and Chen, Chao}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {11659--11669}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/yan21b/yan21b.pdf}, url = {https://proceedings.mlr.press/v139/yan21b.html}, abstract = {Link prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our topological feature, based on the extended persistent homology, encodes rich structural information regarding the multi-hop paths connecting nodes. Based on this feature, we propose a graph neural network method that outperforms state-of-the-arts on different benchmarks. As another contribution, we propose a novel algorithm to more efficiently compute the extended persistence diagrams for graphs. This algorithm can be generally applied to accelerate many other topological methods for graph learning tasks.} }
Endnote
%0 Conference Paper %T Link Prediction with Persistent Homology: An Interactive View %A Zuoyu Yan %A Tengfei Ma %A Liangcai Gao %A Zhi Tang %A Chao Chen %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-yan21b %I PMLR %P 11659--11669 %U https://proceedings.mlr.press/v139/yan21b.html %V 139 %X Link prediction is an important learning task for graph-structured data. In this paper, we propose a novel topological approach to characterize interactions between two nodes. Our topological feature, based on the extended persistent homology, encodes rich structural information regarding the multi-hop paths connecting nodes. Based on this feature, we propose a graph neural network method that outperforms state-of-the-arts on different benchmarks. As another contribution, we propose a novel algorithm to more efficiently compute the extended persistence diagrams for graphs. This algorithm can be generally applied to accelerate many other topological methods for graph learning tasks.
APA
Yan, Z., Ma, T., Gao, L., Tang, Z. & Chen, C.. (2021). Link Prediction with Persistent Homology: An Interactive View. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:11659-11669 Available from https://proceedings.mlr.press/v139/yan21b.html.

Related Material