GraphNAS: Graph Neural Architecture Search with Reinforcement Learning

Abstract

Graph Neural Networks (GNNs) have been popularly used for analyzing non-Euclidean data such as social network data and biological data. Despite their success, the design of graph neural networks requires a lot of manual work and domain knowledge. In this paper, we propose a Graph Neural Architecture Search method (GraphNAS for short) that enables automatic search of the best graph neural architecture based on reinforcement learning. Specifically, GraphNAS first uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks, and then trains the recurrent network with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation data set. Extensive experimental results on node classification tasks in both transductive and inductive learning settings demonstrate that GraphNAS can achieve consistently better performance on the Cora, Citeseer, Pubmed citation network, and protein-protein interaction network. On node classification tasks, GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy.

References in corpus (6)

• Inductive Representation Learning on Large Graphs
• Neural Architecture Search with Reinforcement Learning
• DARTS: Differentiable Architecture Search
• Large-Scale Evolution of Image Classifiers
• Neural Optimizer Search with Reinforcement Learning
• GeniePath: Graph Neural Networks with Adaptive Receptive Paths

Cited by in corpus (21)

• A Survey on Neural Architecture Search
• Design Space for Graph Neural Networks
• Graph Neural Networks: Taxonomy, Advances and Trends
• Auto-GNN: Neural Architecture Search of Graph Neural Networks
• GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
• Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
• Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
• Weight-Sharing Neural Architecture Search: A Battle to Shrink the Optimization Gap
• Graph Random Neural Network for Semi-Supervised Learning on Graphs
• Probabilistic Dual Network Architecture Search on Graphs
• Pre-train and Learn: Preserve Global Information for Graph Neural Networks
• Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
• Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification
• Learned Low Precision Graph Neural Networks
• Evolutionary Architecture Search for Graph Neural Networks
• Policy-GNN: Aggregation Optimization for Graph Neural Networks
• Graph Neural Network Architecture Search for Molecular Property Prediction
• Dimensional Reweighting Graph Convolutional Networks
• Heed the Noise in Performance Evaluations in Neural Architecture Search
• Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification
• Multi-hop Graph Convolutional Network with High-order Chebyshev Approximation for Text Reasoning