Chronobridge: a novel framework for enhanced temporal and relational reasoning in temporal knowledge graphs
Artificial Intelligence Review · 22.10.2024 · 57 (12)
DOI: 10.1007/s10462-024-10983-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift Artificial Intelligence Review, online erschienen am 22.10.2024. Verfasst von Qian Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: The National Key Research and Development Program of China, The National Natural Science Foundation of China project.
Abstract (Originalsprache)
The task of predicting entities and relations in Temporal Knowledge Graph (TKG) extrapolation is crucial and has been studied extensively. Mainstream algorithms, such as Gated Recurrent Unit (GRU) models, primarily focus on encoding historical factual features within TKGs, often neglecting the importance of incorporating entities and relational features during decoding. This bias ultimately leads to loss of detail and inadequate prediction accuracy during the inference process. To address this issue, a novel ChronoBridge framework is proposed that features a dual mechanism of a chronological node encoder and a bridged feature fusion decoder. Specifically, the chronological node encoder employs an advanced recursive neural network with an enhanced GRU in an autoregressive manner to model historical KG sequences, thereby accurately capturing entity changes over time and significantly enhancing the model’s ability to identify and encode temporal patterns of facts across the timeline. Meanwhile, the bridged feature fusion decoder utilizes a new variant of GRU and a multilayer perception mechanism during the prediction phase to extract entity and relation features and fuse them for inference, thereby strengthening the reasoning capabilities of the model for future events. Testing on three standard datasets showed significant improvements, with a 25.21% increase in MRR accuracy and a 39.38% enhancement in relation inference. This advancement not only improves the understanding of temporal evolution in knowledge graphs but also sets a foundation for future research and applications of TKG reasoning.
Förderung
- The National Key Research and Development Program of China
- The National Natural Science Foundation of China project
Zitieren
APA
Liu, Q., Feng, S., Huang, M., & Bhatti, U. A. (2024). Chronobridge: a novel framework for enhanced temporal and relational reasoning in temporal knowledge graphs. Artificial Intelligence Review, 57(12). https://doi.org/10.1007/s10462-024-10983-0
Vancouver
Liu Q, Feng S, Huang M, Bhatti UA. Chronobridge: a novel framework for enhanced temporal and relational reasoning in temporal knowledge graphs. Artificial Intelligence Review. 2024;57(12). doi:10.1007/s10462-024-10983-0
BibTeX
@article{Liu2024,
author = {Liu, Qian and Feng, Siling and Huang, Mengxing and Bhatti, Uzair Aslam},
title = {Chronobridge: a novel framework for enhanced temporal and relational reasoning in temporal knowledge graphs},
journal = {Artificial Intelligence Review},
year = {2024},
volume = {57},
number = {12},
doi = {10.1007/s10462-024-10983-0}
}
EUVIMED