Timezone: »

Neural Approximation of Graph Topological Features
Zuoyu Yan · Tengfei Ma · Liangcai Gao · Zhi Tang · Yusu Wang · Chao Chen

Tue Nov 29 02:00 PM -- 04:00 PM (PST) @ Hall J #224

Topological features based on persistent homology capture high-order structural information so as to augment graph neural network methods. However, computing extended persistent homology summaries remains slow for large and dense graphs and can be a serious bottleneck for the learning pipeline. Inspired by recent success in neural algorithmic reasoning, we propose a novel graph neural network to estimate extended persistence diagrams (EPDs) on graphs efficiently. Our model is built on algorithmic insights, and benefits from better supervision and closer alignment with the EPD computation algorithm. We validate our method with convincing empirical results on approximating EPDs and downstream graph representation learning tasks. Our method is also efficient; on large and dense graphs, we accelerate the computation by nearly 100 times.

Author Information

Zuoyu Yan (Peking University)

Zuoyu Yan received his M.S. degree from Peking University in 2019. He is currently pursuing a Ph.D. degree in Wangxuan Institute of Computer Technology, Peking University. His research interests include persistent homology, graph representation learning, and topological data analysis.

Tengfei Ma (The University of Tokyo)
Liangcai Gao (Peking University)
Zhi Tang (Peking University)
Yusu Wang (University of California, San Diego)
Chao Chen (Stony Brook University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors