A Temporal Knowledge Graph Completion Method Based on Balanced Timestamp Distribution
This work addresses temporal knowledge graph completion for AI applications requiring time-aware reasoning, though it appears incremental as it builds on existing direct encoding frameworks.
The paper tackles the problem of temporal knowledge graph completion by addressing the imbalance in timestamp distribution that limits existing methods, achieving improved performance on real-world datasets.
Completion through the embedding representation of the knowledge graph (KGE) has been a research hotspot in recent years. Realistic knowledge graphs are mostly related to time, while most of the existing KGE algorithms ignore the time information. A few existing methods directly or indirectly encode the time information, ignoring the balance of timestamp distribution, which greatly limits the performance of temporal knowledge graph completion (KGC). In this paper, a temporal KGC method is proposed based on the direct encoding time information framework, and a given time slice is treated as the finest granularity for balanced timestamp distribution. A large number of experiments on temporal knowledge graph datasets extracted from the real world demonstrate the effectiveness of our method.