Continuous Time Bayesian Networks with Clocks

Nicolai Engelmann, Dominik Linzner, Heinz Koeppl
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2912-2921, 2020.

Abstract

Structured stochastic processes evolving in continuous time present a widely adopted framework to model phenomena occurring in nature and engineering. However, such models are often chosen to satisfy the Markov property to maintain tractability. One of the more popular of such memoryless models are Continuous Time Bayesian Networks (CTBNs). In this work, we lift its restriction to exponential survival times to arbitrary distributions. Current extensions achieve this via auxiliary states, which hinder tractability. To avoid that, we introduce a set of node-wise clocks to construct a collection of graph-coupled semi-Markov chains. We provide algorithms for parameter and structure inference, which make use of local dependencies and conduct experiments on synthetic data and a data-set generated through a benchmark tool for gene regulatory networks. In doing so, we point out advantages compared to current CTBN extensions.

Cite this Paper


BibTeX
@InProceedings{pmlr-v119-engelmann20a, title = {Continuous Time {B}ayesian Networks with Clocks}, author = {Engelmann, Nicolai and Linzner, Dominik and Koeppl, Heinz}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {2912--2921}, year = {2020}, editor = {Hal Daumé III and Aarti Singh}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/engelmann20a/engelmann20a.pdf}, url = { http://proceedings.mlr.press/v119/engelmann20a.html }, abstract = {Structured stochastic processes evolving in continuous time present a widely adopted framework to model phenomena occurring in nature and engineering. However, such models are often chosen to satisfy the Markov property to maintain tractability. One of the more popular of such memoryless models are Continuous Time Bayesian Networks (CTBNs). In this work, we lift its restriction to exponential survival times to arbitrary distributions. Current extensions achieve this via auxiliary states, which hinder tractability. To avoid that, we introduce a set of node-wise clocks to construct a collection of graph-coupled semi-Markov chains. We provide algorithms for parameter and structure inference, which make use of local dependencies and conduct experiments on synthetic data and a data-set generated through a benchmark tool for gene regulatory networks. In doing so, we point out advantages compared to current CTBN extensions.} }
Endnote
%0 Conference Paper %T Continuous Time Bayesian Networks with Clocks %A Nicolai Engelmann %A Dominik Linzner %A Heinz Koeppl %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-engelmann20a %I PMLR %P 2912--2921 %U http://proceedings.mlr.press/v119/engelmann20a.html %V 119 %X Structured stochastic processes evolving in continuous time present a widely adopted framework to model phenomena occurring in nature and engineering. However, such models are often chosen to satisfy the Markov property to maintain tractability. One of the more popular of such memoryless models are Continuous Time Bayesian Networks (CTBNs). In this work, we lift its restriction to exponential survival times to arbitrary distributions. Current extensions achieve this via auxiliary states, which hinder tractability. To avoid that, we introduce a set of node-wise clocks to construct a collection of graph-coupled semi-Markov chains. We provide algorithms for parameter and structure inference, which make use of local dependencies and conduct experiments on synthetic data and a data-set generated through a benchmark tool for gene regulatory networks. In doing so, we point out advantages compared to current CTBN extensions.
APA
Engelmann, N., Linzner, D. & Koeppl, H.. (2020). Continuous Time Bayesian Networks with Clocks. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:2912-2921 Available from http://proceedings.mlr.press/v119/engelmann20a.html .

Related Material