From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm

TL;DR

This paper introduces HopGNN, a scalable graph learning paradigm that uses multi-hop features within nodes to improve efficiency and discrimination, addressing limitations of traditional message-passing GNNs.

Contribution

The paper proposes a novel hop interaction paradigm and a HopGNN framework that enhances scalability and discrimination in graph neural networks, with a multi-task self-supervised learning strategy.

Findings

Achieves superior performance on 12 benchmark datasets.

Maintains high scalability and efficiency.

Effectively addresses over-smoothing problem.

Abstract

Existing Graph Neural Networks (GNNs) follow the message-passing mechanism that conducts information interaction among nodes iteratively. While considerable progress has been made, such node interaction paradigms still have the following limitation. First, the scalability limitation precludes the broad application of GNNs in large-scale industrial settings since the node interaction among rapidly expanding neighbors incurs high computation and memory costs. Second, the over-smoothing problem restricts the discrimination ability of nodes, i.e., node representations of different classes will converge to indistinguishable after repeated node interactions. In this work, we propose a novel hop interaction paradigm to address these limitations simultaneously. The core idea is to convert the interaction target among nodes to pre-processed multi-hop features inside each node. We design a simple yet effective HopGNN framework that can easily utilize existing GNNs to achieve hop interaction. Furthermore, we propose a multi-task learning strategy with a self-supervised learning objective to enhance HopGNN. We conduct extensive experiments on 12 benchmark datasets in a wide range of domains, scales, and smoothness of graphs. Experimental results show that our methods achieve superior performance while maintaining high scalability and efficiency. The code is at https://github.com/JC-202/HopGNN.