GraphPAS: Parallel Architecture Search for Graph Neural Networks
This addresses the challenge of efficient architecture search for graph neural networks, which is incremental as it builds on existing methods to speed up the process.
The paper tackles the problem of time-consuming graph neural architecture search for big graph data by proposing GraphPAS, a parallel framework that uses sharing-based evolution learning and dynamic architecture information entropy, resulting in improved efficiency and accuracy compared to state-of-the-art models.
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.