SlotGAT: Slot-based Message Passing for Heterogeneous Graph Neural Network

arXiv:2405.01927v1 Announce Type: new
Abstract: Heterogeneous graphs are ubiquitous to model complex data. There are urgent needs on powerful heterogeneous graph neural networks to effectively support important applications. We identify a potential semantic mixing issue in existing message passing processes, where the representations of the neighbors of a node $v$ are forced to be transformed to the feature space of $v$ for aggregation, though the neighbors are in different types. That is, the semantics in different node types are entangled …

arxiv cs.lg graph graph neural network network neural network type