HIP Network: Historical Information Passing Network for Extrapolation Reasoning on Temporal Knowledge Graph
This work addresses the challenge of extrapolation reasoning for temporal knowledge graphs, which is important for applications like event forecasting, but it appears incremental as it builds on existing methods by enhancing information passing.
The paper tackles the problem of predicting future events in temporal knowledge graphs by proposing the HIP network, which selectively passes historical information from temporal, structural, and repetitive perspectives, resulting in significant improvements in Hits@1 on five benchmark datasets.
In recent years, temporal knowledge graph (TKG) reasoning has received significant attention. Most existing methods assume that all timestamps and corresponding graphs are available during training, which makes it difficult to predict future events. To address this issue, recent works learn to infer future events based on historical information. However, these methods do not comprehensively consider the latent patterns behind temporal changes, to pass historical information selectively, update representations appropriately and predict events accurately. In this paper, we propose the Historical Information Passing (HIP) network to predict future events. HIP network passes information from temporal, structural and repetitive perspectives, which are used to model the temporal evolution of events, the interactions of events at the same time step, and the known events respectively. In particular, our method considers the updating of relation representations and adopts three scoring functions corresponding to the above dimensions. Experimental results on five benchmark datasets show the superiority of HIP network, and the significant improvements on Hits@1 prove that our method can more accurately predict what is going to happen.