RETIA: Relation-Entity Twin-Interact Aggregation for Temporal Knowledge Graph Extrapolation
Authors:
- 1 April 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1761-1774
Abstract
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 relations and entities can make the embeddings of both relations and entities prone to overfitting. To address the abovementioned challenges, we propose an advanced 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). About 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 public datasets show that RETIA has made great improvements across several evaluation metrics. Our released code is available at https://github.com/CGCL-codes/RETIA.Keywords
Funding Information
- National Natural Science Foundation of China
- Australian Research Council
This publication has 23 references indexed in Scilit:
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning2021
- Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs2021
- Message Passing for Hyper-Relational Knowledge Graphs2020
- Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs2020
- End-to-End Structure-Aware Convolutional Networks for Knowledge Base CompletionProceedings of the AAAI Conference on Artificial Intelligence, 2019
- Learning Sequence Encoders for Temporal Knowledge Graph Completion2018
- HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding2018
- Deriving Validity Time in Knowledge Graph2018
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Long Short-Term MemoryNeural Computation, 1997