Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems
Files
(Published version)
Date
2025
Authors
Huang, Z.
Cheng, D.
Liu, L.
Li, J.
Lu, G.
Zhang, S.
Editors
Kwok, J.
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
IJCAI International Joint Conference on Artificial Intelligence, 2025 / Kwok, J. (ed./s), pp.2955-2963
Statement of Responsibility
Conference Name
Thirty-Fourth International Joint Conference on Artificial Intelligence {IJCAI-25} (16 Aug 2025 - 22 Aug 2025 : Montreal, Canada)
Abstract
It is often challenging to identify a valid instrumental variable (IV), although the IV methods have been regarded as effective tools of addressing the confounding bias introduced by latent variables. To deal with this issue, an Interaction-Data-guided Conditional IV (IDCIV) debiasing method is proposed for Recommender Systems, called IDCIV-RS. The IDCIV-RS automatically generates the representations of valid CIVs and their corresponding conditioning sets directly from interaction data, significantly reducing the complexity of IV selection while effectively mitigating the confounding bias caused by latent variables in recommender systems. Specifically, the IDCIV-RS leverages a variational autoencoder (VAE) to learn both the CIV representations and their conditioning sets from interaction data, followed by the application of least squares to derive causal representations for click prediction. Extensive experiments on two real-world datasets, Movielens-10M and Douban-Movie, demonstrate that IDCIV-RS successfully learns the representations of valid CIVs, effectively reduces bias, and consequently improves recommendation accuracy.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
Copyright 2025 The author(s).