Prediction-Centric Learning of Independent Cascade Dynamics from Partial Observations

Mateusz Wilinski, Andrey Lokhov
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:11182-11192, 2021.

Abstract

Spreading processes play an increasingly important role in modeling for diffusion networks, information propagation, marketing and opinion setting. We address the problem of learning of a spreading model such that the predictions generated from this model are accurate and could be subsequently used for the optimization, and control of diffusion dynamics. We focus on a challenging setting where full observations of the dynamics are not available, and standard approaches such as maximum likelihood quickly become intractable for large network instances. We introduce a computationally efficient algorithm, based on a scalable dynamic message-passing approach, which is able to learn parameters of the effective spreading model given only limited information on the activation times of nodes in the network. The popular Independent Cascade model is used to illustrate our approach. We show that tractable inference from the learned model generates a better prediction of marginal probabilities compared to the original model. We develop a systematic procedure for learning a mixture of models which further improves the prediction quality.

Cite this Paper

BibTeX
@InProceedings{pmlr-v139-wilinski21a, title = {Prediction-Centric Learning of Independent Cascade Dynamics from Partial Observations}, author = {Wilinski, Mateusz and Lokhov, Andrey}, booktitle = {Proceedings of the 38th International Conference on Machine Learning}, pages = {11182--11192}, year = {2021}, editor = {Meila, Marina and Zhang, Tong}, volume = {139}, series = {Proceedings of Machine Learning Research}, month = {18--24 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v139/wilinski21a/wilinski21a.pdf}, url = {https://proceedings.mlr.press/v139/wilinski21a.html}, abstract = {Spreading processes play an increasingly important role in modeling for diffusion networks, information propagation, marketing and opinion setting. We address the problem of learning of a spreading model such that the predictions generated from this model are accurate and could be subsequently used for the optimization, and control of diffusion dynamics. We focus on a challenging setting where full observations of the dynamics are not available, and standard approaches such as maximum likelihood quickly become intractable for large network instances. We introduce a computationally efficient algorithm, based on a scalable dynamic message-passing approach, which is able to learn parameters of the effective spreading model given only limited information on the activation times of nodes in the network. The popular Independent Cascade model is used to illustrate our approach. We show that tractable inference from the learned model generates a better prediction of marginal probabilities compared to the original model. We develop a systematic procedure for learning a mixture of models which further improves the prediction quality.} }
Endnote
%0 Conference Paper %T Prediction-Centric Learning of Independent Cascade Dynamics from Partial Observations %A Mateusz Wilinski %A Andrey Lokhov %B Proceedings of the 38th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2021 %E Marina Meila %E Tong Zhang %F pmlr-v139-wilinski21a %I PMLR %P 11182--11192 %U https://proceedings.mlr.press/v139/wilinski21a.html %V 139 %X Spreading processes play an increasingly important role in modeling for diffusion networks, information propagation, marketing and opinion setting. We address the problem of learning of a spreading model such that the predictions generated from this model are accurate and could be subsequently used for the optimization, and control of diffusion dynamics. We focus on a challenging setting where full observations of the dynamics are not available, and standard approaches such as maximum likelihood quickly become intractable for large network instances. We introduce a computationally efficient algorithm, based on a scalable dynamic message-passing approach, which is able to learn parameters of the effective spreading model given only limited information on the activation times of nodes in the network. The popular Independent Cascade model is used to illustrate our approach. We show that tractable inference from the learned model generates a better prediction of marginal probabilities compared to the original model. We develop a systematic procedure for learning a mixture of models which further improves the prediction quality.
APA
Wilinski, M. & Lokhov, A.. (2021). Prediction-Centric Learning of Independent Cascade Dynamics from Partial Observations. Proceedings of the 38th International Conference on Machine Learning, in Proceedings of Machine Learning Research 139:11182-11192 Available from https://proceedings.mlr.press/v139/wilinski21a.html.

Related Material