Abstract: The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network (GNN) models and suggests aggregations ...

GraphAny is a fully-inductive model for node classification. A single trained GraphAny model performs node classification tasks on any graph with any feature and label spaces. Performance-wise, ...

Abstract: Graph convolutional networks (GCNs) have attracted considerable interest in skeleton-based action recognition. Existing GCN-based models have proposed methods to learn dynamic graph ...