RETIA: Relation-Entity Twin-Interact Aggregation for Temporal Knowledge Graph Extrapolation

Temporal knowledge graph (TKG) extrapolation aims to predict future unknown events (facts) based on historical information, and has attracted considerable attention due to its great practical significance. Accurate representations (embeddings) of entities and relations form the basis of TKG extrapolation. Recent work has been devoted to improving the rationality of entity representations. However, on the one hand, ignoring relation modeling results in incomplete relation representations; therefore, some approaches aggregate only immediately adjacent entities of relations, but this can lead to the "message islands" problem of relation modeling. On the other hand, ignoring the association constraints between entities and relations can make the embeddings of both entities and relations prone to overfitting. To address these challenges, we propose a novel method, namely, RETIA. For the former issue, we generate twin hyperrelation subgraphs for each historical subgraph and then aggregate both the adjacent entities and relations in the hyperrelation subgraphs through a graph convolutional network (GCN). For the latter concern, we propose a twin-interact module (TIM), which provides communication channels for relation aggregation and entity aggregation during the evolution of the historical sequence. Experiments conducted on five benchmark datasets demonstrate the substantial improvements achieved by RETIA in terms of multiple evaluation metrics. Our released code is available at https://github.com/CGCL-codes/RETIA.