RTFE: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion
Youri Xu, Haihong E, Meina Song, Wenyu Song, Xiaodong Lv, Wang Haotian, Yang Jinrui
Abstract
Static knowledge graph (SKG) embedding (SKGE) has been studied intensively in the past years. Recently, temporal knowledge graph (TKG) embedding (TKGE) has emerged. In this paper, we propose a Recursive Temporal Fact Embedding (RTFE) framework to transplant SKGE models to TKGs and to enhance the performance of existing TKGE models for TKG completion. Different from previous work which ignores the continuity of states of TKG in time evolution, we treat the sequence of graphs as a Markov chain, which transitions from the previous state to the next state. RTFE takes the SKGE to initialize the embeddings of TKG. Then it recursively tracks the state transition of TKG by passing updated parameters/features between timestamps. Specifically, at each timestamp, we approximate the state transition as the gradient update process. Since RTFE learns each timestamp recursively, it can naturally transit to future timestamps. Experiments on five TKG datasets show the effectiveness of RTFE.
BibTeX
@inproceedings{xu-etal-2021-rtfe,
title = "{RTFE}: A Recursive Temporal Fact Embedding Framework for Temporal Knowledge Graph Completion",
author = "Xu, Youri and
E, Haihong and
Song, Meina and
Song, Wenyu and
Lv, Xiaodong and
Haotian, Wang and
Jinrui, Yang",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.451/",
doi = "10.18653/v1/2021.naacl-main.451",
pages = "5671--5681"
}