Journal
INFORMATION SCIENCES
Volume 621, Issue -, Pages 22-35Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.ins.2022.11.096
Keywords
Confidence score; Pruning strategy; Temporal knowledge graphs; Temporal logical rules
Categories
Ask authors/readers for more resources
This paper introduces a new Temporal Logical reasoning Model (TLmod) that addresses the limitations of existing methods in reasoning paths and achieves excellent performance in two benchmark tests.
Reasoning is essential for the development of large temporal knowledge graphs, which aim to infer new facts based on existing ones. Recent temporal knowledge graph reasoning methods mainly embed timestamps into low-dimensional spaces. These methods focus on entity reasoning, which cannot obtain the specific reasoning paths. More importantly, they ignore the logic and explanation of reasoning paths in temporal knowledge graphs (TKGs). To overcome this limitation, we propose a novel Temporal Logical reasoning Model, denoted as TLmod. This model represents a reasoning process that works through iterative guidance by temporal logical rules. More importantly, we propose two principles of temporal logical rules and define five types of temporal logical rules. Meanwhile, consid-ering the diversity of temporal logical rules, we propose a pruning strategy for obtaining them and calculating the confidence score by combining traversing and random selection. Experimental results show that our model outperforms most metrics compared to prior state-of-the-art baselines across two benchmarks. In addition, analysis of the ablation experiment reveals the validity and importance of temporal logical rules in TKGs.(c) 2022 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available