Data Augmentation for Graph Convolutional Network on Semi-Supervised Classification
This addresses the challenge of data augmentation for graph-based models, which is incremental as it builds on existing GCN methods for semi-supervised classification.
The paper tackled the problem of data augmentation for Graph Convolutional Networks (GCNs) in semi-supervised node classification by generating new graph features and integrating them with an attentional model, resulting in improved classification accuracy by 2.5% to 84.2% over the original GCN across five datasets.
Data augmentation aims to generate new and synthetic features from the original data, which can identify a better representation of data and improve the performance and generalizability of downstream tasks. However, data augmentation for graph-based models remains a challenging problem, as graph data is more complex than traditional data, which consists of two features with different properties: graph topology and node attributes. In this paper, we study the problem of graph data augmentation for Graph Convolutional Network (GCN) in the context of improving the node embeddings for semi-supervised node classification. Specifically, we conduct cosine similarity based cross operation on the original features to create new graph features, including new node attributes and new graph topologies, and we combine them as new pairwise inputs for specific GCNs. Then, we propose an attentional integrating model to weighted sum the hidden node embeddings encoded by these GCNs into the final node embeddings. We also conduct a disparity constraint on these hidden node embeddings when training to ensure that non-redundant information is captured from different features. Experimental results on five real-world datasets show that our method improves the classification accuracy with a clear margin (+2.5% - +84.2%) than the original GCN model.