Local Augmentation for Graph Neural Networks
arXiv:2109.03856
Abstract
Graph Neural Networks (GNNs) have achieved remarkable performance on graph-based tasks. The key idea for GNNs is to obtain informative representation through aggregating information from local neighborhoods. However, it remains an open question whether the neighborhood information is adequately aggregated for learning representations of nodes with few neighbors. To address this, we propose a simple and efficient data augmentation strategy, local augmentation, to learn the distribution of the node features of the neighbors conditioned on the central node's feature and enhance GNN's expressive power with generated features. Local augmentation is a general framework that can be applied to any GNN model in a plug-and-play manner. It samples feature vectors associated with each node from the learned conditional distribution as additional input for the backbone model at each training iteration. Extensive experiments and analyses show that local augmentation consistently yields performance improvement when applied to various GNN architectures across a diverse set of benchmarks. For example, experiments show that plugging in local augmentation to GCN and GAT improves by an average of 3.4\% and 1.6\% in terms of test accuracy on Cora, Citeseer, and Pubmed. Besides, our experimental results on large graphs (OGB) show that our model consistently improves performance over backbones. Code is available at https://github.com/SongtaoLiu0823/LAGNN.
Accepted by ICML'22
References in corpus (11)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Variational Graph Auto-Encoders
- Simple and Deep Graph Convolutional Networks
- Geom-GCN: Geometric Graph Convolutional Networks
- Residual Correlation in Graph Neural Network Regression
- Decoupling the Depth and Scope of Graph Neural Networks
- Batch Virtual Adversarial Training for Graph Convolutional Networks
- Graph Random Neural Network for Semi-Supervised Learning on Graphs
- Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
- Generative Graph Convolutional Network for Growing Graphs
- Data Augmentation for Graph Neural Networks