Rethinking Graph Neural Architecture Search from Message-passing
arXiv:2103.14282
Abstract
Graph neural networks (GNNs) emerged recently as a standard toolkit for learning from data on graphs. Current GNN designing works depend on immense human expertise to explore different message-passing mechanisms, and require manual enumeration to determine the proper message-passing depth. Inspired by the strong searching capability of neural architecture search (NAS) in CNN, this paper proposes Graph Neural Architecture Search (GNAS) with novel-designed search space. The GNAS can automatically learn better architecture with the optimal depth of message passing on the graph. Specifically, we design Graph Neural Architecture Paradigm (GAP) with tree-topology computation procedure and two types of fine-grained atomic operations (feature filtering and neighbor aggregation) from message-passing mechanism to construct powerful graph network search space. Feature filtering performs adaptive feature selection, and neighbor aggregation captures structural information and calculates neighbors' statistics. Experiments show that our GNAS can search for better GNNs with multiple message-passing mechanisms and optimal message-passing depth. The searched network achieves remarkable improvement over state-of-the-art manual designed and search-based GNNs on five large-scale datasets at three classical graph tasks. Codes can be found at https://github.com/phython96/GNAS-MP.
arXiv commentThis paper has been accepted by CVPR2021
References in corpus (13)
- Semi-Supervised Classification with Graph Convolutional Networks
- Neural Architecture Search with Reinforcement Learning
- DARTS: Differentiable Architecture Search
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- Large-Scale Evolution of Image Classifiers
- PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
- Understanding and Robustifying Differentiable Architecture Search
- DARTS+: Improved Differentiable Architecture Search with Early Stopping
- Residual Gated Graph ConvNets
- Benchmarking Graph Neural Networks
- Auto-GNN: Neural Architecture Search of Graph Neural Networks
- DartsReNet: Exploring new RNN cells in ReNet architectures
- PV-NAS: Practical Neural Architecture Search for Video Recognition