Learning How to Propagate Messages in Graph Neural Networks
This addresses a key bottleneck in GNNs for researchers and practitioners by enabling personalized propagation, though it is an incremental improvement over existing methods.
The paper tackles the problem of defining message propagation strategies in graph neural networks (GNNs), which are often not personalized to different nodes or graph types, by proposing a learning framework that learns interpretable and personalized strategies, resulting in significantly better performance on various graph benchmarks compared to state-of-the-art methods.
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.