Dynamic Graph Representation Learning with Fourier Temporal State Embedding

Yihan He, Wei Cao, Shun Zheng, Zhifeng Gao, Jiang Bian

Keywords: Graph Neural Networks, Dynamic Graph, Signal Processing

Abstract: Static graph representation learning has been applied in many tasks over the years thanks to the invention of unsupervised graph embedding methods and more recently, graph neural networks (GNNs). However, in many cases, we are to handle dynamic graphs where the structures of graphs and labels of the nodes are evolving steadily with time. This has posed a great challenge to existing methods in time and memory efficiency. In this work, we present a new method named Fourier Temporal State Embedding (FTSE) to address the temporal information in dynamic graph representation learning. FTSE offered time and memory-efficient solution through applying signal processing techniques to the temporal graph signals. We paired the Fourier Transform with an efficient edge network and provided a new prototype of modeling dynamic graph evolution with high precision. FTSE can also prevent the 'history explosion' that exists in sequential models. The empirical study shows that our proposed approach achieves significantly better performance than previous approaches on public datasets across multiple tasks.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=p9uUnaqVXv