Revisiting Over-smoothing in Graph Neural Networks

Pantelis Elinas, Edwin V. Bonilla

Abstract: Shallow graph neural networks (GNNs) are state-of-the-art models for relational data. However, it is known that deep GNNs suffer from over-smoothing where, as the number of layers increases, node representations become nearly indistinguishable and model performance on the downstream task degrades significantly. Despite multiple approaches being proposed to address this problem, it is unclear when any of these methods (or their combination) works best and how they perform when evaluated under exactly the same experimental setting. In this paper, we systematically and carefully evaluate different methods for alleviating over-smoothing in GNNs. Furthermore, inspired by standard deeply supervised nets, we propose a general architecture that helps alleviate over-smoothing based on the idea of layer-wise supervision. We term this architecture deeply supervised GNNs (or DSGNNs for short). Our experiments show that deeper GNNs can indeed provide better performance when trained on a combination of different approaches and that DSGNNs are robust under various conditions and can provide the best performance in missing-feature scenarios.

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