Beyond Message Passing: Neural Graph Pattern Machine

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Zehong, Zhang, Zheyuan, Ma, Tianyi, Chawla, Nitesh V, Zhang, Chuxu, Ye, Yanfang
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918032933126144
author Wang, Zehong
Zhang, Zheyuan
Ma, Tianyi
Chawla, Nitesh V
Zhang, Chuxu
Ye, Yanfang
author_facet Wang, Zehong
Zhang, Zheyuan
Ma, Tianyi
Chawla, Nitesh V
Zhang, Chuxu
Ye, Yanfang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2501_18739
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Beyond Message Passing: Neural Graph Pattern Machine
Wang, Zehong
Zhang, Zheyuan
Ma, Tianyi
Chawla, Nitesh V
Zhang, Chuxu
Ye, Yanfang
Machine Learning
Artificial Intelligence
Social and Information Networks
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.
title Beyond Message Passing: Neural Graph Pattern Machine
topic Machine Learning
Artificial Intelligence
Social and Information Networks
url https://arxiv.org/abs/2501.18739