Temporal Knowledge Graph Reasoning via Time-Distributed Representation Learning
Authors:
- 1 November 2022
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 279-288
Abstract
Temporal knowledge graph (TKG) reasoning has attracted significant attention. Recent approaches for modeling historical information have led to great advances. However, the problems of time variability and unseen entities have become two major obstacles preventing further development. The time variability problem means that different historical timestamps play different roles in the inference process. Furthermore, in the context of time variability, the unseen entity problem means that a query cannot obtain a predicted entity that is unseen in the scale-varying history rather than in a fixed set, thus turning from static to dynamic. In this paper, we propose a novel method named DHU-NET for addressing the time variability challenge and the dynamic unseen entity challenge derived from it. With regard to the former concern, we propose a time-distributed representation learning method based on a graph convolutional network(GCN) and a self-attention mechanism, which learns the distributed representations of facts at different historical timestamps and comprehensively pays different levels of attention to the different timestamps. With regard to the latter issue, we extract the unseen entities from a global static KG based on a copy mechanism and bring them into consideration during the final prediction step. Experiments on six benchmark datasets demonstrate the substantial improvements achieved by DHUNET in terms of multiple evaluation metrics. Our released codes are available at https://github.com/CGCL-codes/DHUNET.Keywords
Funding Information
- National Natural Science Foundation of China
- Australian Research Council
This publication has 17 references indexed in Scilit:
- Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning2021
- TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting2021
- Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs2021
- 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
- A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network2018
- Deriving Validity Time in Knowledge Graph2018
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014