Neighbour-level message interaction encoding for improved representation learning on graphs

Le résumé fourni par la source

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 information loss in embedding generation. This information loss could accumulate and become more serious as more layers are added to the graph network model. To address this issue, we propose a neighbour-level message interaction information encoding method for improving graph representation learning. For messages that are aggregated at a node, we explicitly generate an encoding between each message and the rest of the messages using an encoding function. Then we aggregate these learned encodings and take the sum of the aggregated encoding and the aggregated message to update the embedding for the node. In this way, neighbour-level message interaction information is integrated into the generated node embeddings. The proposed encoding method is a generic method that can be integrated into message-passing graph convolutional networks. Extensive experiments are conducted on six popular benchmark datasets across four highly-demanded tasks. The results show that integrating neighbour-level message interactions achieves improved performance of the base models, advancing the state of the art results for representation learning over graphs. • This paper introduces message interaction encoding for learning over graphs. • This method addresses the issue of information loss in node embeddings. • It is a general method that can be integrated into different graph neural networks. • It improves the performance on various datasets across different graph tasks.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.