Neighbour-level Message Interaction Encoding for Improved Representation Learning on Graphs

arXiv:2404.09809v1 Announce Type: new
Abstract: Message passing has become the dominant framework in graph representation learning. The essential idea of the message-passing framework is to update node embeddings based on the information aggregated from local neighbours. However, most existing aggregation methods have not encoded neighbour-level message interactions into the aggregated message, resulting in an information lost in embedding generation. And this information lost could be accumulated and become more serious as more layers are added to the graph network model. …

abstract aggregation arxiv become cs.cv cs.lg embeddings encoding framework graph graph representation graphs however information interactions node representation representation learning the information type update