On information dropping and oversmoothing in graph neural networks

Han Xuanyuan, Tianxiang Zhao, Dongsheng Luo

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.

Keywords: Oversmoothing

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We investigate random dropping approaches for addressing the problem of oversmoothing in GNNs

Abstract: Graph Neural Networks (GNNs) are widespread in graph representation learning. *Random dropping* approaches, notably DropEdge and DropMessage, claim to alleviate the key issues of overfitting and oversmoothing by randomly removing elements of the graph representation. However, their effectiveness is largely unverified. In this work, we find experimentally that they have a limited effect in reducing oversmoothing, contrary to what is typically assumed in the literature. These approaches are also non-parametric and motivate us to question if *learned* dropping can alleviate the propagation of redundant or noisy edges. We propose a new information-theoretic approach, in which we learn to perform dropping on the data exchanged by nodes during message passing via optimizing an information bottleneck. Our approach is superior to previous dropping methods in oversmoothing reduction and has promising performance in the case of deep 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.

Submission Number: 8797