TLogic: Temporal Logical Rules for Explainable Link Forecasting on Temporal Knowledge Graphs
This addresses the problem of explainable event prediction in evolving knowledge graphs for AI applications, offering an incremental improvement over existing methods.
The authors tackled link forecasting on temporal knowledge graphs by introducing TLogic, a framework based on temporal logical rules extracted via temporal random walks, achieving better overall performance than state-of-the-art baselines on three benchmark datasets while providing time-consistent explanations.
Conventional static knowledge graphs model entities in relational data as nodes, connected by edges of specific relation types. However, information and knowledge evolve continuously, and temporal dynamics emerge, which are expected to influence future situations. In temporal knowledge graphs, time information is integrated into the graph by equipping each edge with a timestamp or a time range. Embedding-based methods have been introduced for link prediction on temporal knowledge graphs, but they mostly lack explainability and comprehensible reasoning chains. Particularly, they are usually not designed to deal with link forecasting -- event prediction involving future timestamps. We address the task of link forecasting on temporal knowledge graphs and introduce TLogic, an explainable framework that is based on temporal logical rules extracted via temporal random walks. We compare TLogic with state-of-the-art baselines on three benchmark datasets and show better overall performance while our method also provides explanations that preserve time consistency. Furthermore, in contrast to most state-of-the-art embedding-based methods, TLogic works well in the inductive setting where already learned rules are transferred to related datasets with a common vocabulary.