A Novel Graph Aggregation Method Based on Feature Distribution Around Each Ego-node for Heterophily

In this paper, we propose a novel graph aggregation method based on feature distribution around each ego-node (a node to which features are aggregated) for heterophily. In heterophily graphs, labels of neighboring nodes can be uniformly distributed. In such case, aggregated features by existing GNNs will be always similar regardless of the label of ego-node and fail to capture useful information for a node classification task. Since the existing methods basically ignore label distribution around the ego-node, we attempt to handle heterophily graphs through dynamic aggregations so that nodes with similar vicinity characteristics exhibit similar behavior. In particular, we adjust the amount of aggregation based on the features generated by higher-order neighbors, since they reflect the label distribution around each ego-node. By doing this, we can take the influence of distant nodes into account while adapting local structures of each node. Extensive experiments demonstrate that the proposed method achieves higher performance in heterophily graphs by up to 14.68% compared with existing methods.