Search from History and Reason for Future: Two-stage Reasoning on Temporal Knowledge Graphs
This addresses the challenge of future event prediction in temporal knowledge graphs, which is important for applications in areas like recommendation systems and forecasting, but it appears incremental as it builds on existing RL and graph convolution methods.
The paper tackles the problem of predicting future events on Temporal Knowledge Graphs by proposing CluSTeR, a two-stage model that searches historical clues and reasons temporally, achieving substantial advantages over state-of-the-art methods on four datasets.
Temporal Knowledge Graphs (TKGs) have been developed and used in many different areas. Reasoning on TKGs that predicts potential facts (events) in the future brings great challenges to existing models. When facing a prediction task, human beings usually search useful historical information (i.e., clues) in their memories and then reason for future meticulously. Inspired by this mechanism, we propose CluSTeR to predict future facts in a two-stage manner, Clue Searching and Temporal Reasoning, accordingly. Specifically, at the clue searching stage, CluSTeR learns a beam search policy via reinforcement learning (RL) to induce multiple clues from historical facts. At the temporal reasoning stage, it adopts a graph convolution network based sequence method to deduce answers from clues. Experiments on four datasets demonstrate the substantial advantages of CluSTeR compared with the state-of-the-art methods. Moreover, the clues found by CluSTeR further provide interpretability for the results.