Scalable Inference on the Soft Affiliation Graph Model for Overlapping Community Detection

Nishma Laitonjam, Weipeng Huang, Neil J. Hurley
Proceedings of The 12th Asian Conference on Machine Learning, PMLR 129:673-688, 2020.

Abstract

The Soft Affiliation Graph model (S-AGM) is a Bayesian generative model of overlapping community structure in social networks. Inference on this model is challenging due to the complexity of both the underlying network structure and the presence of non-conjugacy in the model. Scalable MCMC on the model is possible through the use of Stochastic Gradient Riemannian Langevin Dynamics (SGRLD). In this paper, we develop a novel and scalable Stochastic Gradient Variational Inference (SG-VI) algorithm and compare it to SGRLD inference. Similarly to MCMC inference, handling non-conjugacy in the S-AGM is a significant challenge for developing an SG-VI and requires the application of stochastic Monte Carlo estimation. We carry out a thorough empirical comparison of the SG-VI and SGRLD approaches, and draw some general conclusions about scalable inference on the S-AGM.

Cite this Paper


BibTeX
@InProceedings{pmlr-v129-laitonjam20a, title = {Scalable Inference on the Soft Affiliation Graph Model for Overlapping Community Detection}, author = {Laitonjam, Nishma and Huang, Weipeng and Hurley, Neil J.}, booktitle = {Proceedings of The 12th Asian Conference on Machine Learning}, pages = {673--688}, year = {2020}, editor = {Pan, Sinno Jialin and Sugiyama, Masashi}, volume = {129}, series = {Proceedings of Machine Learning Research}, month = {18--20 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v129/laitonjam20a/laitonjam20a.pdf}, url = {https://proceedings.mlr.press/v129/laitonjam20a.html}, abstract = {The Soft Affiliation Graph model (S-AGM) is a Bayesian generative model of overlapping community structure in social networks. Inference on this model is challenging due to the complexity of both the underlying network structure and the presence of non-conjugacy in the model. Scalable MCMC on the model is possible through the use of Stochastic Gradient Riemannian Langevin Dynamics (SGRLD). In this paper, we develop a novel and scalable Stochastic Gradient Variational Inference (SG-VI) algorithm and compare it to SGRLD inference. Similarly to MCMC inference, handling non-conjugacy in the S-AGM is a significant challenge for developing an SG-VI and requires the application of stochastic Monte Carlo estimation. We carry out a thorough empirical comparison of the SG-VI and SGRLD approaches, and draw some general conclusions about scalable inference on the S-AGM.} }
Endnote
%0 Conference Paper %T Scalable Inference on the Soft Affiliation Graph Model for Overlapping Community Detection %A Nishma Laitonjam %A Weipeng Huang %A Neil J. Hurley %B Proceedings of The 12th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Sinno Jialin Pan %E Masashi Sugiyama %F pmlr-v129-laitonjam20a %I PMLR %P 673--688 %U https://proceedings.mlr.press/v129/laitonjam20a.html %V 129 %X The Soft Affiliation Graph model (S-AGM) is a Bayesian generative model of overlapping community structure in social networks. Inference on this model is challenging due to the complexity of both the underlying network structure and the presence of non-conjugacy in the model. Scalable MCMC on the model is possible through the use of Stochastic Gradient Riemannian Langevin Dynamics (SGRLD). In this paper, we develop a novel and scalable Stochastic Gradient Variational Inference (SG-VI) algorithm and compare it to SGRLD inference. Similarly to MCMC inference, handling non-conjugacy in the S-AGM is a significant challenge for developing an SG-VI and requires the application of stochastic Monte Carlo estimation. We carry out a thorough empirical comparison of the SG-VI and SGRLD approaches, and draw some general conclusions about scalable inference on the S-AGM.
APA
Laitonjam, N., Huang, W. & Hurley, N.J.. (2020). Scalable Inference on the Soft Affiliation Graph Model for Overlapping Community Detection. Proceedings of The 12th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 129:673-688 Available from https://proceedings.mlr.press/v129/laitonjam20a.html.

Related Material