Dependent Relational Gamma Process Models for Longitudinal Networks

Sikun Yang, Heinz Koeppl
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:5551-5560, 2018.

Abstract

A probabilistic framework based on the covariate-dependent relational gamma process is developed to analyze relational data arising from longitudinal networks. The proposed framework characterizes networked nodes by nonnegative node-group memberships, which allow each node to belong to multiple latent groups simultaneously, and encodes edge probabilities between each pair of nodes using a Bernoulli Poisson link to the embedded latent space. Within the latent space, our framework models the birth and death dynamics of individual groups via a thinning function. Our framework also captures the evolution of individual node-group memberships over time using gamma Markov processes. Exploiting the recent advances in data augmentation and marginalization techniques, a simple and efficient Gibbs sampler is proposed for posterior computation. Experimental results on a simulation study and three real-world temporal network data sets demonstrate the model’s capability, competitive performance and scalability compared to state-of-the-art methods.

Cite this Paper


BibTeX
@InProceedings{pmlr-v80-yang18b, title = {Dependent Relational Gamma Process Models for Longitudinal Networks}, author = {Yang, Sikun and Koeppl, Heinz}, booktitle = {Proceedings of the 35th International Conference on Machine Learning}, pages = {5551--5560}, year = {2018}, editor = {Dy, Jennifer and Krause, Andreas}, volume = {80}, series = {Proceedings of Machine Learning Research}, month = {10--15 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v80/yang18b/yang18b.pdf}, url = {https://proceedings.mlr.press/v80/yang18b.html}, abstract = {A probabilistic framework based on the covariate-dependent relational gamma process is developed to analyze relational data arising from longitudinal networks. The proposed framework characterizes networked nodes by nonnegative node-group memberships, which allow each node to belong to multiple latent groups simultaneously, and encodes edge probabilities between each pair of nodes using a Bernoulli Poisson link to the embedded latent space. Within the latent space, our framework models the birth and death dynamics of individual groups via a thinning function. Our framework also captures the evolution of individual node-group memberships over time using gamma Markov processes. Exploiting the recent advances in data augmentation and marginalization techniques, a simple and efficient Gibbs sampler is proposed for posterior computation. Experimental results on a simulation study and three real-world temporal network data sets demonstrate the model’s capability, competitive performance and scalability compared to state-of-the-art methods.} }
Endnote
%0 Conference Paper %T Dependent Relational Gamma Process Models for Longitudinal Networks %A Sikun Yang %A Heinz Koeppl %B Proceedings of the 35th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2018 %E Jennifer Dy %E Andreas Krause %F pmlr-v80-yang18b %I PMLR %P 5551--5560 %U https://proceedings.mlr.press/v80/yang18b.html %V 80 %X A probabilistic framework based on the covariate-dependent relational gamma process is developed to analyze relational data arising from longitudinal networks. The proposed framework characterizes networked nodes by nonnegative node-group memberships, which allow each node to belong to multiple latent groups simultaneously, and encodes edge probabilities between each pair of nodes using a Bernoulli Poisson link to the embedded latent space. Within the latent space, our framework models the birth and death dynamics of individual groups via a thinning function. Our framework also captures the evolution of individual node-group memberships over time using gamma Markov processes. Exploiting the recent advances in data augmentation and marginalization techniques, a simple and efficient Gibbs sampler is proposed for posterior computation. Experimental results on a simulation study and three real-world temporal network data sets demonstrate the model’s capability, competitive performance and scalability compared to state-of-the-art methods.
APA
Yang, S. & Koeppl, H.. (2018). Dependent Relational Gamma Process Models for Longitudinal Networks. Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research 80:5551-5560 Available from https://proceedings.mlr.press/v80/yang18b.html.

Related Material