Search to aggregate neighborhood for graph neural network

Abstract

Recent years have witnessed the popularity and success of graph neural networks (GNN) in various scenarios. To obtain data-specific GNN architectures, researchers turn to neural architecture search (NAS), which has made impressive success in discovering effective architectures in convolutional neural networks. However, it is non-trivial to apply NAS approaches to GNN due to challenges in search space design and the expensive searching cost of existing NAS methods. In this work, to obtain the data-specific GNN architectures and address the computational challenges facing by NAS approaches, we propose a framework, which tries to Search to Aggregate NEighborhood (SANE), to automatically design data-specific GNN architectures. By designing a novel and expressive search space, we propose a differentiable search algorithm, which is more efficient than previous reinforcement learning based methods. Experimental results on four tasks and seven real-world datasets demonstrate the superiority of SANE compared to existing GNN models and NAS approaches in terms of effectiveness and efficiency. (Code is available at: https://github.com/AutoML-4Paradigm/SANE).

Accepted as a long paper in ICDE 2021

References in corpus (7)

• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Fast Graph Representation Learning with PyTorch Geometric
• Designing Neural Network Architectures using Reinforcement Learning
• Simple and Deep Graph Convolutional Networks
• Geom-GCN: Geometric Graph Convolutional Networks
• BayesNAS: A Bayesian Approach for Neural Architecture Search
• Adaptive Stochastic Natural Gradient Method for One-Shot Neural Architecture Search