A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion

Sylvain Lamprier
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:3632-3641, 2019.

Abstract

Many works have been proposed in the literature to capture the dynamics of diffusion in networks. While some of them define graphical Markovian models to extract temporal relationships between node infections in networks, others consider diffusion episodes as sequences of infections via recurrent neural models. In this paper we propose a model at the crossroads of these two extremes, which embeds the history of diffusion in infected nodes as hidden continuous states. Depending on the trajectory followed by the content before reaching a given node, the distribution of influence probabilities may vary. However, content trajectories are usually hidden in the data, which induces challenging learning problems. We propose a topological recurrent neural model which exhibits good experimental performances for diffusion modeling and prediction.

Cite this Paper

BibTeX
@InProceedings{pmlr-v97-lamprier19a, title = {A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion}, author = {Lamprier, Sylvain}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {3632--3641}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/lamprier19a/lamprier19a.pdf}, url = {https://proceedings.mlr.press/v97/lamprier19a.html}, abstract = {Many works have been proposed in the literature to capture the dynamics of diffusion in networks. While some of them define graphical Markovian models to extract temporal relationships between node infections in networks, others consider diffusion episodes as sequences of infections via recurrent neural models. In this paper we propose a model at the crossroads of these two extremes, which embeds the history of diffusion in infected nodes as hidden continuous states. Depending on the trajectory followed by the content before reaching a given node, the distribution of influence probabilities may vary. However, content trajectories are usually hidden in the data, which induces challenging learning problems. We propose a topological recurrent neural model which exhibits good experimental performances for diffusion modeling and prediction.} }
Endnote
%0 Conference Paper %T A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion %A Sylvain Lamprier %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-lamprier19a %I PMLR %P 3632--3641 %U https://proceedings.mlr.press/v97/lamprier19a.html %V 97 %X Many works have been proposed in the literature to capture the dynamics of diffusion in networks. While some of them define graphical Markovian models to extract temporal relationships between node infections in networks, others consider diffusion episodes as sequences of infections via recurrent neural models. In this paper we propose a model at the crossroads of these two extremes, which embeds the history of diffusion in infected nodes as hidden continuous states. Depending on the trajectory followed by the content before reaching a given node, the distribution of influence probabilities may vary. However, content trajectories are usually hidden in the data, which induces challenging learning problems. We propose a topological recurrent neural model which exhibits good experimental performances for diffusion modeling and prediction.
APA
Lamprier, S.. (2019). A Recurrent Neural Cascade-based Model for Continuous-Time Diffusion. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:3632-3641 Available from https://proceedings.mlr.press/v97/lamprier19a.html.

Related Material