Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction

Yang Hu, Xiyuan Wang, Zhouchen Lin, Pan Li, Muhan Zhang

Abstract: Link prediction is one important application of graph neural networks (GNNs). Most existing GNNs for link prediction are based on one-dimensional Weisfeiler-Lehman ($1$-WL) test. $1$-WL-GNNs first compute node representations by iteratively passing neighboring node features to the center, and then obtain link representations by aggregating the pairwise node representations. As pointed out by previous works, this two-step procedure results in low discriminating power, as $1$-WL-GNNs by nature learn node-level representations instead of link-level. In this paper, we study a completely different approach which can directly obtain node pair (link) representations based on \textit{two-dimensional Weisfeiler-Lehman ($2$-WL) tests}. $2$-WL tests directly use links (2-tuples) as message passing units instead of nodes, and thus can directly obtain link representations. We theoretically analyze the expressive power of $2$-WL tests to discriminate non-isomorphic links, and prove their superior link discriminating power than $1$-WL. Based on different $2$-WL variants, we propose a series of novel $2$-WL-GNN models for link prediction. Experiments on a wide range of real-world datasets demonstrate their competitive performance to state-of-the-art baselines and superiority over plain $1$-WL-GNNs.

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.

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: Yes

Please Choose The Closest Area That Your Submission Falls Into: Deep Learning and representational learning

TL;DR: We propose provably powerful 2-WL variants for link prediction and successfully implement them to get competitive results and speed advantage.