Beyond Message Passing: Neural Graph Pattern Machine

TL;DR

The paper introduces the Neural Graph Pattern Machine (GPM), a framework that directly learns from graph substructures, overcoming message passing limitations to improve expressiveness, long-range dependency modeling, and performance across various graph tasks.

Contribution

GPM is a novel framework that bypasses message passing by explicitly learning from graph substructures, enhancing expressiveness and interpretability.

Findings

GPM outperforms state-of-the-art methods on multiple tasks.

GPM shows strong out-of-distribution generalization.

GPM offers scalability and interpretability benefits.

Abstract

Graph learning tasks often hinge on identifying key substructure patterns -- such as triadic closures in social networks or benzene rings in molecular graphs -- that underpin downstream performance. However, most existing graph neural networks (GNNs) rely on message passing, which aggregates local neighborhood information iteratively and struggles to explicitly capture such fundamental motifs, like triangles, k-cliques, and rings. This limitation hinders both expressiveness and long-range dependency modeling. In this paper, we introduce the Neural Graph Pattern Machine (GPM), a novel framework that bypasses message passing by learning directly from graph substructures. GPM efficiently extracts, encodes, and prioritizes task-relevant graph patterns, offering greater expressivity and improved ability to capture long-range dependencies. Empirical evaluations across four standard tasks -- node classification, link prediction, graph classification, and graph regression -- demonstrate that GPM outperforms state-of-the-art baselines. Further analysis reveals that GPM exhibits strong out-of-distribution generalization, desirable scalability, and enhanced interpretability. Code and datasets are available at: https://github.com/Zehong-Wang/GPM.