Enhancing Intra-class Information Extraction for Heterophilous Graphs: One Neural Architecture Search Approach

TL;DR

This paper introduces IIE-GNN, a neural architecture search-based method that enhances intra-class information extraction in heterophilous graphs by designing node-specific GNN architectures, improving performance over existing approaches.

Contribution

The paper proposes a novel NAS-based framework for designing node-wise GNNs that better extract intra-class information in heterophilous graphs, addressing limitations of previous methods.

Findings

IIE-GNN outperforms existing GNNs on heterophilous graph benchmarks.

Node-wise GNN architectures improve intra-class information extraction.

Neural architecture search effectively customizes GNNs for individual nodes.

Abstract

In recent years, Graph Neural Networks (GNNs) have been popular in graph representation learning which assumes the homophily property, i.e., the connected nodes have the same label or have similar features. However, they may fail to generalize into the heterophilous graphs which in the low/medium level of homophily. Existing methods tend to address this problem by enhancing the intra-class information extraction, i.e., either by designing better GNNs to improve the model effectiveness, or re-designing the graph structures to incorporate more potential intra-class nodes from distant hops. Despite the success, we observe two aspects that can be further improved: (a) enhancing the ego feature information extraction from node itself which is more reliable in extracting the intra-class information; (b) designing node-wise GNNs can better adapt to the nodes with different homophily ratios. In this paper, we propose a novel method IIE-GNN (Intra-class Information Enhanced Graph Neural Networks) to achieve two improvements. A unified framework is proposed based on the literature, in which the intra-class information from the node itself and neighbors can be extracted based on seven carefully designed blocks. With the help of neural architecture search (NAS), we propose a novel search space based on the framework, and then provide an architecture predictor to design GNNs for each node. We further conduct experiments to show that IIE-GNN can improve the model performance by designing node-wise GNNs to enhance intra-class information extraction.