Disentangling Representations from Search Behaviors for Recommendation via Counterfactual Learning
ACM Transactions on Information Systems · 30.06.2026 · 44 (5) · 1-27
DOI: 10.1145/3808226 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 11.06.2026. Verfasst von Jiajun Cui und 7 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
For recommender systems in internet platforms, search activities provide additional insights into user interest through query-click interactions with items, and are thus widely used for enhancing personalized recommendation. However, these interacted items have not only transferable features that match users’ interests and are beneficial to the recommendation domain, but also have features related to users’ unique intents in the search domain. Such a domain gap of item features is neglected by most current search-enhanced recommendation methods. They directly incorporate these search behaviors into recommendation, and thus introduce partial negative transfer. Tackling this problem is challenging due to the lack of explicit supervision signals to disentangle features matching search-specific intent or general interest. To address this, we propose ClardRec, a c ounterfactual l e a rning-driven r epresentation d isentanglement framework for search-enhanced recommendation, based on the common belief that a user would click an item under a query not solely because of the item-query match but also due to the item’s query-independent general features (e.g., color or style) that interest the user. These general features exclude the reflection of search-specific intents contained in queries, ensuring a pure match to users’ underlying interests to complement recommendation. We perform the disentanglement based on a counterfactual thinking idea, how would user preferences and query match change for items if we removed their query-related features in search. Specifically, we leverage search queries to construct counterfactual signals to disentangle item representations, isolating only query-independent general features. These representations subsequently enable feature augmentation and data augmentation for the recommendation scenario. Comprehensive experiments on real datasets demonstrate that ClardRec is effective in both collaborative filtering and sequential recommendation scenarios. The source code is available at https://github.com/JJCui96/ClardRec .
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Cui, J., Chen, X., Xiao, S., Ju, C., Lan, J., Li, T., Wang, J., & Zhang, W. (2026). Disentangling Representations from Search Behaviors for Recommendation via Counterfactual Learning. ACM Transactions on Information Systems, 44(5), 1-27. https://doi.org/10.1145/3808226
Vancouver
Cui J, Chen X, Xiao S, Ju C, Lan J, Li T, et al. Disentangling Representations from Search Behaviors for Recommendation via Counterfactual Learning. ACM Transactions on Information Systems. 2026;44(5):1-27. doi:10.1145/3808226
BibTeX
@article{Cui2026,
author = {Cui, Jiajun and Chen, Xu and Xiao, Shuai and Ju, Chen and Lan, Jinsong and Li, Tingting and Wang, Jianyong and Zhang, Wei},
title = {Disentangling Representations from Search Behaviors for Recommendation via Counterfactual Learning},
journal = {ACM Transactions on Information Systems},
year = {2026},
volume = {44},
number = {5},
pages = {1--27},
doi = {10.1145/3808226}
}
EUVIMED