KatGCN: Knowledge-Aware Attention based Temporal Graph Convolutional Network for Multi-Event Prediction
Xin Song · Proceedings/Proceedings of the ... International Conference on Software Engineering and Knowledge Engineering · 2021
Social events are due to gradually changing relations between entities including citizens, organizations, and national governments.Predicting multiple co-occurring events of different types in the future can help analysts understand social dynamics better and make quick and accurate decisions in advance.However, due to the overlook of the knowledge (e.g., event actors and different relations between them), existing methods are insufficient to model the structural and temporal dependence of events with different types simultaneously to better realize the prediction of future multiple co-occurring events.In the paper, we propose a novel Knowledge-aware attention based temporal Graph Convolutional Network (KatGCN) for predicting multiple co-occurring events of different types.We model social events as temporal event graph and extract static features (e.g., event background, topic keywords) from event content to enhance semantic of event graph.We design knowledge-aware attention based graph aggregation method to capture the structure dependence of co-occurring events with different types.We apply temporal encoding to capture the temporal dependence between temporally adjacent events.Empirical results on five-country datasets show that KatGCN outperforms state-of-the-art methods.Further studies verify the effectiveness and interpretability of our model.