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

Highlights：

• 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.