GraphPAS: Parallel Architecture Search for Graph Neural Networks

Abstract

Graph neural architecture search has received a lot of attention as Graph Neural Networks (GNNs) has been successfully applied on the non-Euclidean data recently. However, exploring all possible GNNs architectures in the huge search space is too time-consuming or impossible for big graph data. In this paper, we propose a parallel graph architecture search (GraphPAS) framework for graph neural networks. In GraphPAS, we explore the search space in parallel by designing a sharing-based evolution learning, which can improve the search efficiency without losing the accuracy. Additionally, architecture information entropy is adopted dynamically for mutation selection probability, which can reduce space exploration. The experimental result shows that GraphPAS outperforms state-of-art models with efficiency and accuracy simultaneously.

arXiv comment5 papes,3 figures,Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

References in corpus (9)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Neural Architecture Search: A Survey
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Fast Graph Representation Learning with PyTorch Geometric
• Large-Scale Learnable Graph Convolutional Networks
• TAGNN: Target Attentive Graph Neural Networks for Session-based Recommendation
• Generalized Score Matching for Non-Negative Data
• Evolutionary Architecture Search for Graph Neural Networks

Cited by in corpus (1)

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