Keywords: temporal point process, temporal graph, dynamic graph, event forecasting, community evoluation
Abstract: Many real-world applications can be formulated as event forecasting on Continuous Time Dynamic Graphs (CTDGs) where the occurrence of a timed event between two entities is represented as an edge along with its occurrence timestamp. However, many previous works handle the problem in compromised settings, either formulating it as a link prediction task on the graph given the event time, or a time prediction problem for which event will happen next. In this paper, we propose a novel model combining Graph Neural Networks and Marked Temporal Point Process (MTPP) that jointly forecasts multiple link events and their timestamps on communities over a CTDG. Moreover, to scale our model to large graphs, we factorize the joint event prediction problem into three easier conditional probability modeling problems. To evaluate the effectiveness of our model and the rationale behind such a decomposition, we establish a set of benchmarks and evaluation metrics. The experimental results demonstrate the superiority of our model in terms of both accuracy and training efficiency. All the source codes and datasets are available in a GitHub repository.
Type Of Submission: Full paper proceedings track submission (max 9 main pages).
TL;DR: We present a novel community event forecasting task on temporal graphs and a new model to tackle this problem utilizing GNNs. We also address the scalability problem and reduce complexity when formulating the temporal point process on graph.
PDF File: pdf
Agreement: Check this if you are okay with being contacted to participate in an anonymous survey.
Type Of Submission: Full paper proceedings track submission.
Poster Preview: png