Causal GraphSAGE: A robust graph method for classification based on causal sampling

•Introduces causal inference into GraphSAGE to improve the robustness of GraphSAGE's classification performance.•Proposes a novel causal sampling algorithm using causal bootstrap weights of the neighborhood of a node. Compared with the original uniform random sampling of GraphSAGE, the nodes obtained by such causal sampling select the most robust neighbors for the subsequent aggregation operation.•Causal sampling focuses not only on the structure around the target node, but also on the structural characteristics of neighbors and their labels, making the embedding of nodes in Causal-GraphSAGE more robust. GraphSAGE is a widely-used graph neural network for classification, which generates node embeddings in two steps: sampling and aggregation. In this paper, we introduce causal inference into the GraphSAGE sampling stage, and propose Causal GraphSAGE (C-GraphSAGE) to improve the robustness of the classifier. In C-GraphSAGE, we use causal bootstrapping to obtain a weighting between the target node's neighbors and their label. Then, these weights are used to resample the node's neighbors to enforce the robustness of the sampling stage. Finally, an aggregation function is trained to integrate the features of the selected neighbors to obtain the embedding of the target node. Experimental results on the Cora, Pubmed, and Citeseer citation datasets show that the classification performance of C-GraphSAGE is equivalent to that of GraphSAGE, GCN, GAT, and RL-GraphSAGE in the case of no perturbation, and outperforms these as the perturbation ratio increases.