Learning Hawkes Processes from Short Doubly-Censored Event Sequences

Hongteng Xu, Dixin Luo, Hongyuan Zha
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:3831-3840, 2017.

Abstract

Many real-world applications require robust algorithms to learn point process models based on a type of incomplete data — the so-called short doubly-censored (SDC) event sequences. In this paper, we study this critical problem of quantitative asynchronous event sequence analysis under the framework of Hawkes processes by leveraging the general idea of data synthesis. In particular, given SDC event sequences observed in a variety of time intervals, we propose a sampling-stitching data synthesis method — sampling predecessor and successor for each SDC event sequence from potential candidates and stitching them together to synthesize long training sequences. The rationality and the feasibility of our method are discussed in terms of arguments based on likelihood. Experiments on both synthetic and real-world data demonstrate that the proposed data synthesis method improves learning results indeed for both time-invariant and time-varying Hawkes processes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-xu17b, title = {Learning {H}awkes Processes from Short Doubly-Censored Event Sequences}, author = {Hongteng Xu and Dixin Luo and Hongyuan Zha}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {3831--3840}, year = {2017}, editor = {Precup, Doina and Teh, Yee Whye}, volume = {70}, series = {Proceedings of Machine Learning Research}, month = {06--11 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v70/xu17b/xu17b.pdf}, url = {https://proceedings.mlr.press/v70/xu17b.html}, abstract = {Many real-world applications require robust algorithms to learn point process models based on a type of incomplete data — the so-called short doubly-censored (SDC) event sequences. In this paper, we study this critical problem of quantitative asynchronous event sequence analysis under the framework of Hawkes processes by leveraging the general idea of data synthesis. In particular, given SDC event sequences observed in a variety of time intervals, we propose a sampling-stitching data synthesis method — sampling predecessor and successor for each SDC event sequence from potential candidates and stitching them together to synthesize long training sequences. The rationality and the feasibility of our method are discussed in terms of arguments based on likelihood. Experiments on both synthetic and real-world data demonstrate that the proposed data synthesis method improves learning results indeed for both time-invariant and time-varying Hawkes processes.} }
Endnote
%0 Conference Paper %T Learning Hawkes Processes from Short Doubly-Censored Event Sequences %A Hongteng Xu %A Dixin Luo %A Hongyuan Zha %B Proceedings of the 34th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2017 %E Doina Precup %E Yee Whye Teh %F pmlr-v70-xu17b %I PMLR %P 3831--3840 %U https://proceedings.mlr.press/v70/xu17b.html %V 70 %X Many real-world applications require robust algorithms to learn point process models based on a type of incomplete data — the so-called short doubly-censored (SDC) event sequences. In this paper, we study this critical problem of quantitative asynchronous event sequence analysis under the framework of Hawkes processes by leveraging the general idea of data synthesis. In particular, given SDC event sequences observed in a variety of time intervals, we propose a sampling-stitching data synthesis method — sampling predecessor and successor for each SDC event sequence from potential candidates and stitching them together to synthesize long training sequences. The rationality and the feasibility of our method are discussed in terms of arguments based on likelihood. Experiments on both synthetic and real-world data demonstrate that the proposed data synthesis method improves learning results indeed for both time-invariant and time-varying Hawkes processes.
APA
Xu, H., Luo, D. & Zha, H.. (2017). Learning Hawkes Processes from Short Doubly-Censored Event Sequences. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:3831-3840 Available from https://proceedings.mlr.press/v70/xu17b.html.

Related Material