Learning How to Propagate Messages in Graph Neural Networks

TL;DR

This paper introduces a novel learning framework for graph neural networks that explicitly learns personalized message propagation strategies, improving performance and interpretability across various graph benchmarks.

Contribution

It proposes a variational EM-based framework to learn interpretable, personalized propagation strategies for GNNs, addressing the challenge of fixed, non-adaptive message passing.

Findings

Significantly outperforms state-of-the-art methods on multiple benchmarks.

Effectively learns personalized message propagation strategies.

Enhances interpretability of GNN message passing.

Abstract

This paper studies the problem of learning message propagation strategies for graph neural networks (GNNs). One of the challenges for graph neural networks is that of defining the propagation strategy. For instance, the choices of propagation steps are often specialized to a single graph and are not personalized to different nodes. To compensate for this, in this paper, we present learning to propagate, a general learning framework that not only learns the GNN parameters for prediction but more importantly, can explicitly learn the interpretable and personalized propagate strategies for different nodes and various types of graphs. We introduce the optimal propagation steps as latent variables to help find the maximum-likelihood estimation of the GNN parameters in a variational Expectation-Maximization (VEM) framework. Extensive experiments on various types of graph benchmarks demonstrate that our proposed framework can significantly achieve better performance compared with the state-of-the-art methods, and can effectively learn personalized and interpretable propagate strategies of messages in GNNs.