Communicative Message Passing for Inductive Relation Reasoning
Keywords:Linked Open Data, Knowledge Graphs & KB Completio, Graph Mining, Social Network Analysis & Community
AbstractRelation prediction for knowledge graphs aims at predicting missing relationships between entities. Despite the importance of inductive relation prediction, most previous works are limited to a transductive setting and cannot process previously unseen entities. The recent proposed subgraph-based relation reasoning models provided alternatives to predict links from the subgraph structure surrounding a candidate triplet inductively. However, we observe that these methods often neglect the directed nature of the extracted subgraph and weaken the role of relation information in the subgraph modeling. As a result, they fail to effectively handle the asymmetric/anti-symmetric triplets and produce insufficient embeddings for the target triplets. To this end, we introduce a Communicative Message Passing neural network for Inductive reLation rEasoning, CoMPILE, that reasons over local directed subgraph structures and has a vigorous inductive bias to process entity-independent semantic relations. In contrast to existing models, CoMPILE strengthens the message interactions between edges and entitles through a communicative kernel and enables a sufficient flow of relation information. Moreover, we demonstrate that CoMPILE can naturally handle asymmetric/anti-symmetric relations without the need for explosively increasing the number of model parameters by extracting the directed enclosing subgraphs. Extensive experiments show substantial performance gains in comparison to state-of-the-art methods on commonly used benchmark datasets with variant inductive settings.
How to Cite
Mai, S., Zheng, S., Yang, Y., & Hu, H. (2021). Communicative Message Passing for Inductive Relation Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4294-4302. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16554
AAAI Technical Track on Data Mining and Knowledge Management