CataBEEM: Integrating Latent Interaction Categories in Node-wise Community Detection Models for Network Data

Yuhua Zhang, Walter H. Dempsey
Proceedings of the 40th International Conference on Machine Learning, PMLR 202:40946-40975, 2023.

Abstract

Community detection is a fundamental task in network analysis. Learning underlying network structures has brought deep insights into the understanding of complex systems. While many methods have focused on clustering nodes into blocks, few accounts for the fact that interactions may exhibit edge-level clustering, which we call categories. Real network data often arise via a series of interactions. Interactions in complex systems can often be clustered into different categories and node-level community structures that depend on the category. In this paper, we introduce a category-and-block edge exchangeable model (CataBEEM) to study interaction networks with joint latent interaction-level category and node-level community structures. In particular, the proposed method models the network from the interaction process perspective and allows the incorporation of prior knowledge from auxiliary interaction-wise information. We derive an efficient variational inference algorithm that can be applied to networks consisting of millions of interactions and provide the theoretical bound of the misspecification rate. We demonstrate the effectiveness of our method in various simulation settings and apply the method to TalkLife data, a large-scale online peer-to-peer support network. We show CataBEEM detects more temporally consistent community structures and has better predictions than other methods.

Cite this Paper

BibTeX
@InProceedings{pmlr-v202-zhang23h, title = {{C}ata{BEEM}: Integrating Latent Interaction Categories in Node-wise Community Detection Models for Network Data}, author = {Zhang, Yuhua and Dempsey, Walter H.}, booktitle = {Proceedings of the 40th International Conference on Machine Learning}, pages = {40946--40975}, year = {2023}, editor = {Krause, Andreas and Brunskill, Emma and Cho, Kyunghyun and Engelhardt, Barbara and Sabato, Sivan and Scarlett, Jonathan}, volume = {202}, series = {Proceedings of Machine Learning Research}, month = {23--29 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v202/zhang23h/zhang23h.pdf}, url = {https://proceedings.mlr.press/v202/zhang23h.html}, abstract = {Community detection is a fundamental task in network analysis. Learning underlying network structures has brought deep insights into the understanding of complex systems. While many methods have focused on clustering nodes into blocks, few accounts for the fact that interactions may exhibit edge-level clustering, which we call categories. Real network data often arise via a series of interactions. Interactions in complex systems can often be clustered into different categories and node-level community structures that depend on the category. In this paper, we introduce a category-and-block edge exchangeable model (CataBEEM) to study interaction networks with joint latent interaction-level category and node-level community structures. In particular, the proposed method models the network from the interaction process perspective and allows the incorporation of prior knowledge from auxiliary interaction-wise information. We derive an efficient variational inference algorithm that can be applied to networks consisting of millions of interactions and provide the theoretical bound of the misspecification rate. We demonstrate the effectiveness of our method in various simulation settings and apply the method to TalkLife data, a large-scale online peer-to-peer support network. We show CataBEEM detects more temporally consistent community structures and has better predictions than other methods.} }
Endnote
%0 Conference Paper %T CataBEEM: Integrating Latent Interaction Categories in Node-wise Community Detection Models for Network Data %A Yuhua Zhang %A Walter H. Dempsey %B Proceedings of the 40th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2023 %E Andreas Krause %E Emma Brunskill %E Kyunghyun Cho %E Barbara Engelhardt %E Sivan Sabato %E Jonathan Scarlett %F pmlr-v202-zhang23h %I PMLR %P 40946--40975 %U https://proceedings.mlr.press/v202/zhang23h.html %V 202 %X Community detection is a fundamental task in network analysis. Learning underlying network structures has brought deep insights into the understanding of complex systems. While many methods have focused on clustering nodes into blocks, few accounts for the fact that interactions may exhibit edge-level clustering, which we call categories. Real network data often arise via a series of interactions. Interactions in complex systems can often be clustered into different categories and node-level community structures that depend on the category. In this paper, we introduce a category-and-block edge exchangeable model (CataBEEM) to study interaction networks with joint latent interaction-level category and node-level community structures. In particular, the proposed method models the network from the interaction process perspective and allows the incorporation of prior knowledge from auxiliary interaction-wise information. We derive an efficient variational inference algorithm that can be applied to networks consisting of millions of interactions and provide the theoretical bound of the misspecification rate. We demonstrate the effectiveness of our method in various simulation settings and apply the method to TalkLife data, a large-scale online peer-to-peer support network. We show CataBEEM detects more temporally consistent community structures and has better predictions than other methods.
APA
Zhang, Y. & Dempsey, W.H.. (2023). CataBEEM: Integrating Latent Interaction Categories in Node-wise Community Detection Models for Network Data. Proceedings of the 40th International Conference on Machine Learning, in Proceedings of Machine Learning Research 202:40946-40975 Available from https://proceedings.mlr.press/v202/zhang23h.html.

Related Material