Graph Random Neural Network for Semi-Supervised Learning on Graphs
arXiv:2005.11079
Abstract
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored. However, most existing GNNs inherently suffer from the limitations of over-smoothing, non-robustness, and weak-generalization when labeled nodes are scarce. In this paper, we propose a simple yet effective framework -- GRAPH RANDOM NEURAL NETWORKS (GRAND) -- to address these issues. In GRAND, we first design a random propagation strategy to perform graph data augmentation. Then we leverage consistency regularization to optimize the prediction consistency of unlabeled nodes across different data augmentations. Extensive experiments on graph benchmark datasets suggest that GRAND significantly outperforms state-of-the-art GNN baselines on semi-supervised node classification. Finally, we show that GRAND mitigates the issues of over-smoothing and non-robustness, exhibiting better generalization behavior than existing GNNs. The source code of GRAND is publicly available at https://github.com/Grand20/grand.
arXiv comment18 pages. NeurIPS 2020 Oral. Final version
References in corpus (21)
- Adam: A Method for Stochastic Optimization
- Semi-Supervised Classification with Graph Convolutional Networks
- mixup: Beyond Empirical Risk Minimization
- Neural Message Passing for Quantum Chemistry
- Spectral Networks and Locally Connected Networks on Graphs
- Unsupervised Data Augmentation for Consistency Training
- Deep Convolutional Networks on Graph-Structured Data
- Simplifying Graph Convolutional Networks
- Adversarial Attacks on Neural Networks for Graph Data
- Representation Learning on Graphs with Jumping Knowledge Networks
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- Pitfalls of Graph Neural Network Evaluation
- MixMatch: A Holistic Approach to Semi-Supervised Learning
- FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
- MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
- Dropout Training as Adaptive Regularization
- PairNorm: Tackling Oversmoothing in GNNs
- Adaptive Sampling Towards Fast Graph Representation Learning
- GraphNAS: Graph Neural Architecture Search with Reinforcement Learning
- Batch Virtual Adversarial Training for Graph Convolutional Networks
- A Flexible Generative Framework for Graph-based Semi-supervised Learning