Deep Generative Models for Relational Data with Side Information

Changwei Hu, Piyush Rai, Lawrence Carin
Proceedings of the 34th International Conference on Machine Learning, PMLR 70:1578-1586, 2017.

Abstract

We present a probabilistic framework for overlapping community discovery and link prediction for relational data, given as a graph. The proposed framework has: (1) a deep architecture which enables us to infer multiple layers of latent features/communities for each node, providing superior link prediction performance on more complex networks and better interpretability of the latent features; and (2) a regression model which allows directly conditioning the node latent features on the side information available in form of node attributes. Our framework handles both (1) and (2) via a clean, unified model, which enjoys full local conjugacy via data augmentation, and facilitates efficient inference via closed form Gibbs sampling. Moreover, inference cost scales in the number of edges which is attractive for massive but sparse networks. Our framework is also easily extendable to model weighted networks with count-valued edges. We compare with various state-of-the-art methods and report results, both quantitative and qualitative, on several benchmark data sets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v70-hu17d, title = {Deep Generative Models for Relational Data with Side Information}, author = {Changwei Hu and Piyush Rai and Lawrence Carin}, booktitle = {Proceedings of the 34th International Conference on Machine Learning}, pages = {1578--1586}, 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/hu17d/hu17d.pdf}, url = {https://proceedings.mlr.press/v70/hu17d.html}, abstract = {We present a probabilistic framework for overlapping community discovery and link prediction for relational data, given as a graph. The proposed framework has: (1) a deep architecture which enables us to infer multiple layers of latent features/communities for each node, providing superior link prediction performance on more complex networks and better interpretability of the latent features; and (2) a regression model which allows directly conditioning the node latent features on the side information available in form of node attributes. Our framework handles both (1) and (2) via a clean, unified model, which enjoys full local conjugacy via data augmentation, and facilitates efficient inference via closed form Gibbs sampling. Moreover, inference cost scales in the number of edges which is attractive for massive but sparse networks. Our framework is also easily extendable to model weighted networks with count-valued edges. We compare with various state-of-the-art methods and report results, both quantitative and qualitative, on several benchmark data sets.} }
Endnote
%0 Conference Paper %T Deep Generative Models for Relational Data with Side Information %A Changwei Hu %A Piyush Rai %A Lawrence Carin %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-hu17d %I PMLR %P 1578--1586 %U https://proceedings.mlr.press/v70/hu17d.html %V 70 %X We present a probabilistic framework for overlapping community discovery and link prediction for relational data, given as a graph. The proposed framework has: (1) a deep architecture which enables us to infer multiple layers of latent features/communities for each node, providing superior link prediction performance on more complex networks and better interpretability of the latent features; and (2) a regression model which allows directly conditioning the node latent features on the side information available in form of node attributes. Our framework handles both (1) and (2) via a clean, unified model, which enjoys full local conjugacy via data augmentation, and facilitates efficient inference via closed form Gibbs sampling. Moreover, inference cost scales in the number of edges which is attractive for massive but sparse networks. Our framework is also easily extendable to model weighted networks with count-valued edges. We compare with various state-of-the-art methods and report results, both quantitative and qualitative, on several benchmark data sets.
APA
Hu, C., Rai, P. & Carin, L.. (2017). Deep Generative Models for Relational Data with Side Information. Proceedings of the 34th International Conference on Machine Learning, in Proceedings of Machine Learning Research 70:1578-1586 Available from https://proceedings.mlr.press/v70/hu17d.html.

Related Material