Optimal Transport Alignment of User Preferences from Ratings and Texts

Nhu-Thuat Tran, Hady W. Lauw
Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, PMLR 286:4251-4265, 2025.

Abstract

Modeling hidden factors driving user preferences is crucial for recommendation yet challenging due to sparse rating data. While aligning preference factors from ratings and texts, as a solution, shows improvements, existing methods impose restrictive one-to-one factor correspondences and underutilize cross-modal interest signals. We propose an optimal transport (OT) approach to address these gaps. By modeling rating- and text-based preference factors as distributions, we compute an OT plan that captures their probabilistic relationships. This plan serves dual roles: 1) to regularize cross-modal preference factors without rigid correspondence assumptions, and 2) to blend preference signals across modalities through barycentric mapping. Experiments on real-world datasets validate our method’s effectiveness over competitive baselines, highlighting its novel use of OT for adaptive preference factor alignment, an underexplored direction in recommender system research.

Cite this Paper

BibTeX
@InProceedings{pmlr-v286-tran25a, title = {Optimal Transport Alignment of User Preferences from Ratings and Texts}, author = {Tran, Nhu-Thuat and Lauw, Hady W.}, booktitle = {Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence}, pages = {4251--4265}, year = {2025}, editor = {Chiappa, Silvia and Magliacane, Sara}, volume = {286}, series = {Proceedings of Machine Learning Research}, month = {21--25 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v286/main/assets/tran25a/tran25a.pdf}, url = {https://proceedings.mlr.press/v286/tran25a.html}, abstract = {Modeling hidden factors driving user preferences is crucial for recommendation yet challenging due to sparse rating data. While aligning preference factors from ratings and texts, as a solution, shows improvements, existing methods impose restrictive one-to-one factor correspondences and underutilize cross-modal interest signals. We propose an optimal transport (OT) approach to address these gaps. By modeling rating- and text-based preference factors as distributions, we compute an OT plan that captures their probabilistic relationships. This plan serves dual roles: 1) to regularize cross-modal preference factors without rigid correspondence assumptions, and 2) to blend preference signals across modalities through barycentric mapping. Experiments on real-world datasets validate our method’s effectiveness over competitive baselines, highlighting its novel use of OT for adaptive preference factor alignment, an underexplored direction in recommender system research.} }
Endnote
%0 Conference Paper %T Optimal Transport Alignment of User Preferences from Ratings and Texts %A Nhu-Thuat Tran %A Hady W. Lauw %B Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2025 %E Silvia Chiappa %E Sara Magliacane %F pmlr-v286-tran25a %I PMLR %P 4251--4265 %U https://proceedings.mlr.press/v286/tran25a.html %V 286 %X Modeling hidden factors driving user preferences is crucial for recommendation yet challenging due to sparse rating data. While aligning preference factors from ratings and texts, as a solution, shows improvements, existing methods impose restrictive one-to-one factor correspondences and underutilize cross-modal interest signals. We propose an optimal transport (OT) approach to address these gaps. By modeling rating- and text-based preference factors as distributions, we compute an OT plan that captures their probabilistic relationships. This plan serves dual roles: 1) to regularize cross-modal preference factors without rigid correspondence assumptions, and 2) to blend preference signals across modalities through barycentric mapping. Experiments on real-world datasets validate our method’s effectiveness over competitive baselines, highlighting its novel use of OT for adaptive preference factor alignment, an underexplored direction in recommender system research.
APA
Tran, N. & Lauw, H.W.. (2025). Optimal Transport Alignment of User Preferences from Ratings and Texts. Proceedings of the Forty-first Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research 286:4251-4265 Available from https://proceedings.mlr.press/v286/tran25a.html.

Related Material