Current studentsExisting staffContact us
 

Learning instrumental variable representation for debiasing in recommender systems

Simple item page
dc.contributor.authorHuang, Z.
dc.contributor.authorZhang, S.
dc.contributor.authorCheng, D.
dc.contributor.authorLi, J.
dc.contributor.authorLiu, L.
dc.contributor.authorLu, G.
dc.contributor.authorZhang, G.
dc.date.issued2026
dc.description.abstractRecommender systems are essential for filtering content to match user preferences. However, traditional recommender systems often suffer from biases inherent in the data, such as popularity bias. These biases, particularly those stemming from latent confounders, can result in inaccurate recommendations and reduce both the diversity and effectiveness of the system. Existing debiasing methods for recommender systems, however, either fail to account for latent confounders or rely on predefined instrumental variables (IVs). To address this research gap, we propose a novel causality-based recommendation algorithm, Data-driven IV representation learning for debiasing in Recommender System (DIVRS), which enables the learning of IV representation directly from user-item interaction data. By leveraging the learned IV representation, DIVRS decomposes user behaviour into causal and confounding relationships to address potential bias in recommender systems. Additionally, we introduce Orthogonal Promotion Regularisation (OPR) for DIVRS to address the problem that Graph Convolutional Networks (GCNs) amplify bias. We also propose a variant of GCNs for DIVRS, called DIVRS-GCN. Experimental results on the Douban-Movie and Movielens-10M datasets demonstrate that both DIVRS and DIVRS-GCN effectively mitigate confounding bias while outperform the state-of-the-art methods in recommendation performance. For example, on both datasets, our DIVRS and DIVRS-GCN improve Recall@20 by up to 10.98 %. This validates their effectiveness and robustness. Our approaches improve recommendation accuracy while delivering more balanced and diverse suggestions, effectively addressing the limitations of existing IV-based recommender systems.
dc.identifier.citationNeural Networks, 2026; 193(107977):1-13
dc.identifier.doi10.1016/j.neunet.2025.107977
dc.identifier.issn0893-6080
dc.identifier.issn1879-2782
dc.identifier.urihttps://hdl.handle.net/11541.2/44361
dc.language.isoen
dc.publisherElsevier
dc.relation.fundingARC 230101122
dc.relation.fundingResearch Fund of Guangxi Key Lab of Multi-source Information Mining & Security MIMS24-M-01
dc.relation.fundingResearch Fund of Guangxi Key Lab of Multi-source Information Mining & Security 24-A-01-02
dc.relation.fundingProject of Guangxi Science and Technology GuiKeAB23026040
dc.rightsCopyright 2025 Elsevier Access Condition Notes: Accepted manuscript available after 1 October 2027
dc.source.urihttps://doi.org/10.1016/j.neunet.2025.107977
dc.subjectconfounding bias
dc.subjectinstrumental variable
dc.subjectlatent confounders
dc.subjectrecommender systems
dc.titleLearning instrumental variable representation for debiasing in recommender systems
dc.typeJournal article
pubs.publication-statusPublished
ror.fileinfo12306786760001831 13306786750001831 Open Access Postprint
ror.mmsid9917067631001831

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
9917067631001831_12306786760001831_AM 9917067631001831.pdf
Size:
540.47 KB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections