Contextualized Messages Boost Graph Representations

Brian Godwin Lim, Galvin Brice Sy Lim, Renzo Roel Tan, Kazushi Ikeda

Keywords: deep learning, graph neural network, representational capability, soft-isomorphic relational graph convolution network

TL;DR: We theoretically justify the need for anisotropic and dynamic messages in GNNs and propose a computationally efficient model satisfying this requirement that empirically outperforms comparable models.

Abstract: Graph neural networks (GNNs) have gained significant attention in recent years for their ability to process data that may be represented as graphs. This has prompted several studies to explore their representational capability based on the graph isomorphism task. These works inherently assume a countable node feature representation, potentially limiting their applicability. Interestingly, only a few study GNNs with uncountable node feature representation. In the paper, a novel perspective on the representational capability of GNNs is investigated across all levels—node-level, neighborhood-level, and graph-level—when the space of node feature representation is uncountable. More specifically, the strict injective and metric requirements are *softly* relaxed by employing a *pseudometric* distance on the space of input to create a *soft-injective* function such that distinct inputs may produce *similar* outputs if and only if the *pseudometric* deems the inputs to be sufficiently *similar* on some representation. As a consequence, a simple and computationally efficient *soft-isomorphic* relational graph convolution network (SIR-GCN) that emphasizes the contextualized transformation of neighborhood feature representations via *anisotropic* and *dynamic* message functions is proposed. A mathematical discussion on the relationship between SIR-GCN and widely used GNNs is then laid out to put the contribution into context, establishing SIR-GCN as a generalization of classical GNN methodologies. Experiments on synthetic and benchmark datasets then demonstrate the relative superiority of SIR-GCN, outperforming comparable models in node and graph property prediction tasks.

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: 7053