DeepAI AI Chat
Log In Sign Up

Auto-HeG: Automated Graph Neural Network on Heterophilic Graphs

by   Xin Zheng, et al.
Haerbin institute of technology Shenzhen Graduate School
Monash University
Shenzhen University
Griffith University

Graph neural architecture search (NAS) has gained popularity in automatically designing powerful graph neural networks (GNNs) with relieving human efforts. However, existing graph NAS methods mainly work under the homophily assumption and overlook another important graph property, i.e., heterophily, which exists widely in various real-world applications. To date, automated heterophilic graph learning with NAS is still a research blank to be filled in. Due to the complexity and variety of heterophilic graphs, the critical challenge of heterophilic graph NAS mainly lies in developing the heterophily-specific search space and strategy. Therefore, in this paper, we propose a novel automated graph neural network on heterophilic graphs, namely Auto-HeG, to automatically build heterophilic GNN models with expressive learning abilities. Specifically, Auto-HeG incorporates heterophily into all stages of automatic heterophilic graph learning, including search space design, supernet training, and architecture selection. Through the diverse message-passing scheme with joint micro-level and macro-level designs, we first build a comprehensive heterophilic GNN search space, enabling Auto-HeG to integrate complex and various heterophily of graphs. With a progressive supernet training strategy, we dynamically shrink the initial search space according to layer-wise variation of heterophily, resulting in a compact and efficient supernet. Taking a heterophily-aware distance criterion as the guidance, we conduct heterophilic architecture selection in the leave-one-out pattern, so that specialized and expressive heterophilic GNN architectures can be derived. Extensive experiments illustrate the superiority of Auto-HeG in developing excellent heterophilic GNNs to human-designed models and graph NAS models.


page 1

page 2

page 3

page 4


Simplifying Architecture Search for Graph Neural Network

Recent years have witnessed the popularity of Graph Neural Networks (GNN...

Efficient and Explainable Graph Neural Architecture Search via Monte-Carlo Tree Search

Graph neural networks (GNNs) are powerful tools for performing data scie...

Search to aggregate neighborhood for graph neural network

Recent years have witnessed the popularity and success of graph neural n...

Graph Neural Network Architecture Search for Molecular Property Prediction

Predicting the properties of a molecule from its structure is a challeng...

Search to Pass Messages for Temporal Knowledge Graph Completion

Completing missing facts is a fundamental task for temporal knowledge gr...

Learned Low Precision Graph Neural Networks

Deep Graph Neural Networks (GNNs) show promising performance on a range ...

Probabilistic Dual Network Architecture Search on Graphs

We present the first differentiable Network Architecture Search (NAS) fo...