Search For Deep Graph Neural Networks

Abstract

Current GNN-oriented NAS methods focus on the search for different layer aggregate components with shallow and simple architectures, which are limited by the 'over-smooth' problem. To further explore the benefits from structural diversity and depth of GNN architectures, we propose a GNN generation pipeline with a novel two-stage search space, which aims at automatically generating high-performance while transferable deep GNN models in a block-wise manner. Meanwhile, to alleviate the 'over-smooth' problem, we incorporate multiple flexible residual connection in our search space and apply identity mapping in the basic GNN layers. For the search algorithm, we use deep-q-learning with epsilon-greedy exploration strategy and reward reshaping. Extensive experiments on real-world datasets show that our generated GNN models outperforms existing manually designed and NAS-based ones.

References in corpus (10)

• DARTS: Differentiable Architecture Search
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Pitfalls of Graph Neural Network Evaluation
• Interaction Networks for Learning about Objects, Relations and Physics
• Graph Neural Networks with convolutional ARMA filters
• Designing Neural Network Architectures using Reinforcement Learning
• Simple and Deep Graph Convolutional Networks
• SIGN: Scalable Inception Graph Neural Networks
• Geom-GCN: Geometric Graph Convolutional Networks
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks