SlenderGNN: Accurate, Robust, and Interpretable GNN, and the Reasons for its Success

Jaemin Yoo, Meng-Chieh Lee, Shubhranshu Shekhar, Christos Faloutsos

Keywords: Graph neural networks, Linear models, Node classification, Heterophily graphs, Lightweight models

TL;DR: We propose SlenderGNN, a linear GNN whose motivations are derived from comprehensive linearization on existing models.

Abstract: Can we design a GNN that is accurate and interpretable at the same time? Could it also be robust to handle the case of homophily, heterophily, or even noisy edges without network effects? We propose SlenderGNN that has all desirable properties: (a) accurate, (b) robust, and (c) interpretable. For the reasons of its success, we had to dig deeper: The result is our GNNLIN framework which highlights the fundamental differences among popular GNN models (e.g., feature combination, structural normalization, etc.) and thus reveals the reasons for the success of our SlenderGNN, as well as the reasons for occasional failures of other GNN variants. Thanks to our careful design, SlenderGNN passes all the 'sanity checks' we propose, and it achieves the highest overall accuracy on 9 real-world datasets of both homophily and heterophily graphs, when compared against 10 recent GNN models. Specifically, SlenderGNN exceeds the accuracy of linear GNNs and matches or exceeds the accuracy of nonlinear models with up to 64 times fewer parameters.

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: General Machine Learning (ie none of the above)