Memory-based Message Passing: Decoupling the Message for Propogation from Discrimination

TL;DR

This paper introduces Memory-based Message Passing (MMP), a novel approach for graph neural networks that decouples message discrimination from propagation, improving performance on noisy and non-smooth graphs.

Contribution

The paper proposes a general MMP method that separates node discrimination from message propagation, with a control mechanism and regularization, enhancing GNN robustness.

Findings

MMP improves GNN performance on diverse datasets.

MMP is effective across different homophily ratios.

The method enhances robustness to noisy graphs.

Abstract

Message passing is a fundamental procedure for graph neural networks in the field of graph representation learning. Based on the homophily assumption, the current message passing always aggregates features of connected nodes, such as the graph Laplacian smoothing process. However, real-world graphs tend to be noisy and/or non-smooth. The homophily assumption does not always hold, leading to sub-optimal results. A revised message passing method needs to maintain each node's discriminative ability when aggregating the message from neighbors. To this end, we propose a Memory-based Message Passing (MMP) method to decouple the message of each node into a self-embedding part for discrimination and a memory part for propagation. Furthermore, we develop a control mechanism and a decoupling regularization to control the ratio of absorbing and excluding the message in the memory for each node. More importantly, our MMP is a general skill that can work as an additional layer to help improve traditional GNNs performance. Extensive experiments on various datasets with different homophily ratios demonstrate the effectiveness and robustness of the proposed method.