Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation

Wang, X; Li, Q; Yu, D; Li, Q; Xu, G

Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation

Wang, X Li, Q Yu, D

Li, Q Xu, G

Permalink

Publisher:: Association for Computing Machinery (ACM)
Publication Type:: Journal Article
Citation:: ACM Transactions on Recommender Systems

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Accepted versionAdobe PDF (3.74 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, X
dc.contributor.author	Li, Q
dc.contributor.author	Yu, D https://orcid.org/0000-0001-6376-9667
dc.contributor.author	Li, Q
dc.contributor.author	Xu, G
dc.date.accessioned	2024-02-06T23:46:08Z
dc.date.available	2024-02-06T23:46:08Z
dc.identifier.citation	ACM Transactions on Recommender Systems
dc.identifier.issn	2770-6699
dc.identifier.issn	2770-6699
dc.identifier.uri	http://hdl.handle.net/10453/175409
dc.description.abstract	<jats:p> Fairness-aware recommendation eliminates discrimination issues to build trustworthy recommendation systems. Existing fairness-aware approaches ignore accounting for rich user and item attributes and thus cannot capture the impact of attributes on affecting recommendation fairness. These real-world attributes severely cause unfair recommendations by favoring items with popular attributes, leading to item exposure unfairness in recommendations. Moreover, existing approaches mostly mitigate unfairness for static recommendation models, e.g., collaborative filtering. Static models can not handle dynamic user interactions with the system that reflect users’ preferences shift through time. Thus, static models are limited in their ability to adapt to user behavior shifts to gain long-run user satisfaction. As user and item attributes are largely involved in modern recommenders and user interactions are naturally dynamic, it is essential to develop a novel method that eliminates unfairness caused by attributes meanwhile embrace the dynamic modeling of user behavior shifts. In this paper, we propose <jats:italic>Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation (Fair-HINpolicy)</jats:italic> , which uses recent advances in context-aware off-policy learning to produce fairness-aware recommendations with rich attributes from a Heterogeneous Information Network. In particular, we formulate the off-policy learning as a Constrained Markov Decision Process (CMDP) by dynamically constraining the fairness of item exposure at each iteration. We also design an attentive action sampling to reduce the search space for off-policy learning. Our solution adaptively receives HIN-augmented corrections for counterfactual risk minimization, and ultimately yields an effective policy that maximizes long-term user satisfaction. We extensively evaluate our method through simulations on large-scale real-world datasets, obtaining favorable results compared with state-of-the-art methods. </jats:p>
dc.language	en
dc.publisher	Association for Computing Machinery (ACM)
dc.relation.ispartof	ACM Transactions on Recommender Systems
dc.relation.isbasedon	10.1145/3629172
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	“©ACM2023. This is the author’s version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in 26 October 2023 https://doi.org/10.1145/3629172”
dc.title	Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation
dc.type	Journal Article
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	open_access	*
dc.date.updated	2024-02-06T23:46:07Z
pubs.publication-status	Published online

Abstract:

Fairness-aware recommendation eliminates discrimination issues to build trustworthy recommendation systems. Existing fairness-aware approaches ignore accounting for rich user and item attributes and thus cannot capture the impact of attributes on affecting recommendation fairness. These real-world attributes severely cause unfair recommendations by favoring items with popular attributes, leading to item exposure unfairness in recommendations. Moreover, existing approaches mostly mitigate unfairness for static recommendation models, e.g., collaborative filtering. Static models can not handle dynamic user interactions with the system that reflect users’ preferences shift through time. Thus, static models are limited in their ability to adapt to user behavior shifts to gain long-run user satisfaction. As user and item attributes are largely involved in modern recommenders and user interactions are naturally dynamic, it is essential to develop a novel method that eliminates unfairness caused by attributes meanwhile embrace the dynamic modeling of user behavior shifts. In this paper, we propose Constrained Off-policy Learning over Heterogeneous Information for Fairness-aware Recommendation (Fair-HINpolicy) , which uses recent advances in context-aware off-policy learning to produce fairness-aware recommendations with rich attributes from a Heterogeneous Information Network. In particular, we formulate the off-policy learning as a Constrained Markov Decision Process (CMDP) by dynamically constraining the fairness of item exposure at each iteration. We also design an attentive action sampling to reduce the search space for off-policy learning. Our solution adaptively receives HIN-augmented corrections for counterfactual risk minimization, and ultimately yields an effective policy that maximizes long-term user satisfaction. We extensively evaluate our method through simulations on large-scale real-world datasets, obtaining favorable results compared with state-of-the-art methods.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/175409