TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph
A typical multi-hop temporal complex query and its computation graph: “During François Hollande was the president of France, which countries did Xi Jinping visit but Barack Obama did not visit?”. In the computation graph, there are entity set (blue circle), timestamp set (green triangle), time set projection (green arrow), entity set projection (blue arrow) and logical operators (red rectangle).Abstract
Multi-hop logical reasoning over knowledge graph plays a fundamental role in many artificial intelligence tasks. Recent complex query embedding methods for reasoning focus on static KGs, while temporal knowledge graphs have not been fully explored. Reasoning over TKGs has two challenges: 1. The query should answer entities or timestamps; 2. The operators should consider both set logic on entity set and temporal logic on timestamp set. To bridge this gap, we introduce the multi-hop logical reasoning problem on TKGs and then propose the first temporal complex query embedding named Temporal Feature-Logic Embedding framework (TFLEX) to answer the temporal complex queries. Specifically, we utilize fuzzy logic to compute the logic part of the Temporal Feature-Logic embedding, thus naturally modeling all first-order logic operations on the entity set. In addition, we further extend fuzzy logic on timestamp set to cope with three extra temporal operators (After, Before and Between). Experiments on numerous query patterns demonstrate the effectiveness of our method.
Challenges: 1）TKGC: One-hop 👍 multi-hop&logical ❌ 2）Complex Reasoning over static KG: ignoring time, while most knowledge and facts are temporal❌
we introduce a temporal multi-hop logical reasoning task over TKGs. The task aims to answer temporal complex queries, which have two main distinctions from existing queries over static KGs. Firstly, the answer sets for queries over TKGs are either entity sets or timestamp sets, while that for existing queries over static KGs can only be entity sets. Secondly, as temporal information is included in the query, temporal operators such as After, Before should be considered apart from FOL operators.
Contribution
- The definition of multi-hop logical reasoning task over TKGs is given.
- We propose the first multi-hop logical reasoning framework on TKGs.
- We generate 3 new TKG datasets for the task.