Stick-Breaking Embedded Topic Model with Continuous Optimal Transport for Online Analysis of Document Streams

Federica Granese, Serena Villata, Charles Bouveyron
Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, PMLR 300:3106-3114, 2026.

Abstract

Online topic models are unsupervised algorithms to identify latent topics in data streams that continuously evolve over time. Although these methods naturally align with real-world scenarios, they have received considerably less attention from the community compared to their offline counterparts, due to specific additional challenges. To tackle these issues, we present SB-SETM, an innovative model extending the Embedded Topic Model (ETM) to process data streams by merging models formed on successive partial document batches. To this end, SB-SETM (i) leverages a truncated stick-breaking construction for the topic–per-document distribution, enabling the model to automatically infer from the data the appropriate number of active topics at each timestep; and (ii) introduces a merging strategy for topic embeddings based on a continuous formulation of optimal transport adapted to the high dimensionality of the latent topic space. Numerical experiments show SB-SETM outperforming baselines on simulated scenarios. We extensively test it on a real-world corpus of news articles covering the Russian–Ukrainian war throughout 2022–2023.

Cite this Paper

BibTeX
@InProceedings{pmlr-v300-granese26a, title = { Stick-Breaking Embedded Topic Model with Continuous Optimal Transport for Online Analysis of Document Streams }, author = {Granese, Federica and Villata, Serena and Bouveyron, Charles}, booktitle = {Proceedings of The 29th International Conference on Artificial Intelligence and Statistics}, pages = {3106--3114}, year = {2026}, editor = {Khan, Emtiyaz and Li, Yingzhen and Solin, Arno and Ramdas, Aaditya}, volume = {300}, series = {Proceedings of Machine Learning Research}, month = {02--05 May}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v300/main/assets/granese26a/granese26a.pdf}, url = {https://proceedings.mlr.press/v300/granese26a.html}, abstract = { Online topic models are unsupervised algorithms to identify latent topics in data streams that continuously evolve over time. Although these methods naturally align with real-world scenarios, they have received considerably less attention from the community compared to their offline counterparts, due to specific additional challenges. To tackle these issues, we present SB-SETM, an innovative model extending the Embedded Topic Model (ETM) to process data streams by merging models formed on successive partial document batches. To this end, SB-SETM (i) leverages a truncated stick-breaking construction for the topic–per-document distribution, enabling the model to automatically infer from the data the appropriate number of active topics at each timestep; and (ii) introduces a merging strategy for topic embeddings based on a continuous formulation of optimal transport adapted to the high dimensionality of the latent topic space. Numerical experiments show SB-SETM outperforming baselines on simulated scenarios. We extensively test it on a real-world corpus of news articles covering the Russian–Ukrainian war throughout 2022–2023. } }
Endnote
%0 Conference Paper %T Stick-Breaking Embedded Topic Model with Continuous Optimal Transport for Online Analysis of Document Streams %A Federica Granese %A Serena Villata %A Charles Bouveyron %B Proceedings of The 29th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2026 %E Emtiyaz Khan %E Yingzhen Li %E Arno Solin %E Aaditya Ramdas %F pmlr-v300-granese26a %I PMLR %P 3106--3114 %U https://proceedings.mlr.press/v300/granese26a.html %V 300 %X Online topic models are unsupervised algorithms to identify latent topics in data streams that continuously evolve over time. Although these methods naturally align with real-world scenarios, they have received considerably less attention from the community compared to their offline counterparts, due to specific additional challenges. To tackle these issues, we present SB-SETM, an innovative model extending the Embedded Topic Model (ETM) to process data streams by merging models formed on successive partial document batches. To this end, SB-SETM (i) leverages a truncated stick-breaking construction for the topic–per-document distribution, enabling the model to automatically infer from the data the appropriate number of active topics at each timestep; and (ii) introduces a merging strategy for topic embeddings based on a continuous formulation of optimal transport adapted to the high dimensionality of the latent topic space. Numerical experiments show SB-SETM outperforming baselines on simulated scenarios. We extensively test it on a real-world corpus of news articles covering the Russian–Ukrainian war throughout 2022–2023.
APA
Granese, F., Villata, S. & Bouveyron, C.. (2026). Stick-Breaking Embedded Topic Model with Continuous Optimal Transport for Online Analysis of Document Streams . Proceedings of The 29th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 300:3106-3114 Available from https://proceedings.mlr.press/v300/granese26a.html.

Related Material