Path and Structural Features Enhanced Reinforcement Learning for Knowledge Graph Completion
Applied Sciences · 02.04.2026 · 16 (7) · 3460
DOI: 10.3390/app16073460 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 02.04.2026. Verfasst von Weidong Li und 4 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Scientific and Technological Innovation Team Program for Young and Middle-Aged Researchers in Hubei Higher Education Institutions, Startup Project of Doctor scientific research.
Abstract (Originalsprache)
The knowledge graph plays an important role in the construction of artificial intelligence applications. However, the incompleteness of the knowledge graph seriously affects the performance of downstream applications. The problem has fueled a lot of researches on knowledge graph completion (also known as the tasks of link prediction). Reinforcement learning-based multi-hop reasoning that formulates link prediction as a sequential decision problem has also become an interesting and promising approach. Nevertheless, in an incomplete knowledge graph environment, the policy-based agent might travel a large number of low-quality or spurious search trajectories, which inhibits the model performance. Therefore, in this paper, we propose a path and structural features-enhanced reinforcement learning model (referred as PGATRL). First, we leverage the path constraint resource allocation algorithm to mine high-quality inference paths, which can be employed to pre-train the LSTM path encoder module in the reinforcement learning architecture, and thus play a role in guiding the agent’s action decision-making. Second, we exploit the adapted graph attention networks to encode the local structural features of an entity, which can provide more evidence for the agent to find a more suitable reasoning path. With extensive experiments on several benchmark datasets, our proposed approach gains significant improvements compared with the state-of-the-art baselines.
Förderung
- National Natural Science Foundation of China
- Scientific and Technological Innovation Team Program for Young and Middle-Aged Researchers in Hubei Higher Education Institutions
- Startup Project of Doctor scientific research
Zitieren
APA
Li, W., Wang, Z., Ye, Z., Mo, S., & Luo, G. (2026). Path and Structural Features Enhanced Reinforcement Learning for Knowledge Graph Completion. Applied Sciences, 16(7), 3460. https://doi.org/10.3390/app16073460
Vancouver
Li W, Wang Z, Ye Z, Mo S, Luo G. Path and Structural Features Enhanced Reinforcement Learning for Knowledge Graph Completion. Applied Sciences. 2026;16(7):3460. doi:10.3390/app16073460
BibTeX
@article{Li2026,
author = {Li, Weidong and Wang, Zhizhi and Ye, Zhiwei and Mo, Shengjun and Luo, Guiyou},
title = {Path and Structural Features Enhanced Reinforcement Learning for Knowledge Graph Completion},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {7},
pages = {3460},
doi = {10.3390/app16073460}
}
EUVIMED