Link Prediction with Untrained Message Passing Layers

Lisi Qarkaxhija, Anatol Eugen Wegner, Ingo Scholtes

Keywords: graph neural networks, untrained message passing layers, link prediction, path-based similarity measures

TL;DR: Untrained message passing layers in graph neural networks outperform trained counterparts for link prediction, offering efficiency and interpretability, especially with high-dimensional features.

Abstract: In this work, we explore the use of untrained message passing layers in graph neural networks for link prediction. The untrained message passing layers we consider are derived from widely used graph neural network architectures by removing trainable parameters and nonlinearities in their respective message passing layers. Experimentally we find that untrained message passing layers can lead to competitive and even superior link prediction performance compared to fully trained message passing layers while being more efficient and naturally interpretable, especially in the presence of high-dimensional features. We also provide a theoretical analysis of untrained message passing layers in the context of link prediction and show that the inner product of features produced by untrained message passing layers relate to common neighbour and path-based topological measures which are widely used for link prediction. As such, untrained message passing layers offer a more efficient and interpretable alternative to trained message passing layers in link 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.

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: 6304