Towards Dynamic Graph Neural Networks with Provably High-Order Expressive Power

Zhe Wang, Tianjian Zhao, Zhen Zhang, Jiawei Chen, Sheng Zhou, Yan Feng, Chun Chen, Can Wang

Keywords: Graph Neural Network, Dynamic Graph, Expressive power

TL;DR: We propose a dynamic graph neural network with provably high-order expressive power.

Abstract:

Dynamic Graph Neural Networks (DyGNNs) have garnered increasing research attention for learning representations on evolving graphs.
Despite their effectiveness, the limited expressive power of existing DyGNNs hinders them from capturing important evolving patterns of dynamic graphs.
Although some works attempt to enhance expressive capability with heuristic features, there remains a lack of DyGNN frameworks with provable and quantifiable high-order expressive power.
To address this research gap, we firstly propose the k-dimensional Dynamic WL tests (k-DWL) as the referencing algorithms to quantify the expressive power of DyGNNs. We demonstrate that the expressive power of existing DyGNNs is bounded by the 1-DWL test.
To enhance the expressive power, we propose Dynamic Graph Neural Network with High-order expressive power (HopeDGN), which updates the representation of central node pair by aggregating the interaction history with neighbor node pairs.
Our theoretical results demonstrate that HopeDGN can achieve expressive power equivalent to the 2-DWL test.
We then present a Transformer-based implementation for the local variant of \model.
Experimental results show that HopeDGN achieved performance improvement up to 3.12\% on seven datasets, demonstrating the effectiveness of HopeDGN.

Primary Area: learning on graphs and other geometries & topologies

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.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2481