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

by   Lanning Wei, et al.

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.


page 1

page 2

page 3

page 4


Edge-featured Graph Neural Architecture Search

Graph neural networks (GNNs) have been successfully applied to learning ...

Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective

In recent years, Graph Neural Networks (GNNs) have shown superior perfor...

GraTO: Graph Neural Network Framework Tackling Over-smoothing with Neural Architecture Search

Current Graph Neural Networks (GNNs) suffer from the over-smoothing prob...

Evolving Computation Graphs

Graph neural networks (GNNs) have demonstrated success in modeling relat...

When Do Graph Neural Networks Help with Node Classification: Investigating the Homophily Principle on Node Distinguishability

Homophily principle, i.e. nodes with the same labels are more likely to ...

Deep Active Graph Representation Learning

Graph neural networks (GNNs) aim to learn graph representations that pre...

Learn Layer-wise Connections in Graph Neural Networks

In recent years, Graph Neural Networks (GNNs) have shown superior perfor...

Please sign up or login with your details

Forgot password? Click here to reset