Simplifying Architecture Search for Graph Neural Network

By Huan Zhao, Lanning Wei, Quanming Yao. 2020

59 citations recorded by the source corpus.

Recent years have witnessed the popularity of Graph Neural Networks (GNN) in various scenarios. To obtain optimal data-specific GNN architectures, researchers turn to neural architecture search (NAS) methods, which have made impressive progress in discovering effective architectures in convolutional neural networks. Two preliminary works, GraphNAS and Auto-GNN, have made first attempt to apply NAS methods to GNN. Despite the promising results, there are several drawbacks in expressive capability and search efficiency of GraphNAS and Auto-GNN due to the designed search space. To overcome these drawbacks, we propose the SNAG framework (Simplified Neural Architecture search for Graph neural networks), consisting of a novel search space and a reinforcement learning based search algorithm. Extensive experiments on real-world datasets demonstrate the effectiveness of the SNAG framework compared to human-designed GNNs and NAS methods, including GraphNAS and Auto-GNN.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Huan Zhao
2. Lan Wei
3. Quanming Yao
4. Zhiqiang He

In Computer Vision and Pattern Recognition

1. Huan Zhao
2. Lan Wei
3. Quanming Yao
4. Zhiqiang He

Citations in the corpus

• Pooling Architecture Search for Graph Classification (2021, methodology): “(a) GraphNAS [12] : a RL based method which design different aggregation operations in each layer; (b) GraphNAS-WS: GraphNAS with the weight sharing schema [33]; (c) SNAG [57] : a RL based method which design node aggregations, skip connections and layer aggregations in GNNs; (d) SNAG-WS: SNAG with ”