CEP3: Community Event Prediction With Neural Point Process on Graph

Xuhong Wang, Sirui Chen, Yixuan He, Minjie Wang, Quan Gan, Junchi Yan
Proceedings of the First Learning on Graphs Conference, PMLR 198:39:1-39:17, 2022.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v198-wang22c, title = {CEP3: Community Event Prediction With Neural Point Process on Graph}, author = {Wang, Xuhong and Chen, Sirui and He, Yixuan and Wang, Minjie and Gan, Quan and Yan, Junchi}, booktitle = {Proceedings of the First Learning on Graphs Conference}, pages = {39:1--39:17}, year = {2022}, editor = {Rieck, Bastian and Pascanu, Razvan}, volume = {198}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v198/wang22c/wang22c.pdf}, url = {https://proceedings.mlr.press/v198/wang22c.html}, 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. } }
Endnote
%0 Conference Paper %T CEP3: Community Event Prediction With Neural Point Process on Graph %A Xuhong Wang %A Sirui Chen %A Yixuan He %A Minjie Wang %A Quan Gan %A Junchi Yan %B Proceedings of the First Learning on Graphs Conference %C Proceedings of Machine Learning Research %D 2022 %E Bastian Rieck %E Razvan Pascanu %F pmlr-v198-wang22c %I PMLR %P 39:1--39:17 %U https://proceedings.mlr.press/v198/wang22c.html %V 198 %X 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.
APA
Wang, X., Chen, S., He, Y., Wang, M., Gan, Q. & Yan, J.. (2022). CEP3: Community Event Prediction With Neural Point Process on Graph. Proceedings of the First Learning on Graphs Conference, in Proceedings of Machine Learning Research 198:39:1-39:17 Available from https://proceedings.mlr.press/v198/wang22c.html.

Related Material