IMF: Interpretable Multi-Hop Forecasting on Temporal Knowledge Graphs
Entropy · 16.04.2023 · 25 (4) · 666
DOI: 10.3390/e25040666 ↗Kurz gefasst
Fachartikel in der Zeitschrift Entropy, online erschienen am 16.04.2023. Verfasst von Zhenyu Du und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Temporal knowledge graphs (KGs) have recently attracted increasing attention. The temporal KG forecasting task, which plays a crucial role in such applications as event prediction, predicts future links based on historical facts. However, current studies pay scant attention to the following two aspects. First, the interpretability of current models is manifested in providing reasoning paths, which is an essential property of path-based models. However, the comparison of reasoning paths in these models is operated in a black-box fashion. Moreover, contemporary models utilize separate networks to evaluate paths at different hops. Although the network for each hop has the same architecture, each network achieves different parameters for better performance. Different parameters cause identical semantics to have different scores, so models cannot measure identical semantics at different hops equally. Inspired by the observation that reasoning based on multi-hop paths is akin to answering questions step by step, this paper designs an Interpretable Multi-Hop Reasoning (IMR) framework based on consistent basic models for temporal KG forecasting. IMR transforms reasoning based on path searching into stepwise question answering. In addition, IMR develops three indicators according to the characteristics of temporal KGs and reasoning paths: the question matching degree, answer completion level, and path confidence. IMR can uniformly integrate paths of different hops according to the same criteria; IMR can provide the reasoning paths similarly to other interpretable models and further explain the basis for path comparison. We instantiate the framework based on common embedding models such as TransE, RotatE, and ComplEx. While being more explainable, these instantiated models achieve state-of-the-art performance against previous models on four baseline datasets.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China.
ORCID-Profile: Lin Cui
Zitieren
APA
Du, Z., Qu, L., Liang, Z., Huang, K., Cui, L., & Gao, Z. (2023). IMF: Interpretable Multi-Hop Forecasting on Temporal Knowledge Graphs. Entropy, 25(4), 666. https://doi.org/10.3390/e25040666
Vancouver
Du Z, Qu L, Liang Z, Huang K, Cui L, Gao Z. IMF: Interpretable Multi-Hop Forecasting on Temporal Knowledge Graphs. Entropy. 2023;25(4):666. doi:10.3390/e25040666
BibTeX
@article{Du2023,
author = {Du, Zhenyu and Qu, Lingzhi and Liang, Zongwei and Huang, Keju and Cui, Lin and Gao, Zhiyang},
title = {IMF: Interpretable Multi-Hop Forecasting on Temporal Knowledge Graphs},
journal = {Entropy},
year = {2023},
volume = {25},
number = {4},
pages = {666},
doi = {10.3390/e25040666}
}
EUVIMED