TY - GEN
T1 - Link Prediction with Persistent Homology
T2 - 38th International Conference on Machine Learning, ICML 2021
AU - Yan, Zuoyu
AU - Ma, Tengfei
AU - Gao, Liangcai
AU - Tang, Zhi
AU - Chen, Chao
N1 - Publisher Copyright:
Copyright © 2021 by the author(s)
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85117796340
M3 - Conference contribution
AN - SCOPUS:85117796340
T3 - Proceedings of Machine Learning Research
SP - 11659
EP - 11669
BT - Proceedings of the 38th International Conference on Machine Learning, ICML 2021
PB - ML Research Press
Y2 - 18 July 2021 through 24 July 2021
ER -