Scalable Message Passing Neural Networks: No Need for Attention in Large Graph Representation Learning

Haitz Sáez de Ocáriz Borde, Artem Lukoianov, Anastasis Kratsios, Michael M. Bronstein, Xiaowen Dong

Keywords: Message Passing Neural Networks, Graph Representation Learning, Large Graphs

Abstract: We propose Scalable Message Passing Neural Networks (SMPNNs) and demonstrate that, by integrating standard convolutional message passing into a Pre-Layer Normalization Transformer-style block instead of attention, we can produce high-performing deep message-passing-based Graph Neural Networks (GNNs). This modification yields state-of-the-art results in large graph transductive learning, outperforming the best Graph Transformers in the literature without requiring the otherwise computationally and memory-expensive attention. Our architecture not only scales to large graphs but also makes it possible to construct deep message-passing networks, unlike simple GNNs, which have traditionally been constrained to shallow architectures due to oversmoothing. Moreover, we provide a new theoretical analysis of oversmoothing based on universal approximation which we use to motivate SMPNNs.

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.

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: 11277