Proceedings

Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems

Zhirong Huang, Debo Cheng, Lin Liu, Jiuyong Li, Guangquan Lu, Shichao Zhang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 2955-2963.

https://doi.org/10.24963/ijcai.2025/329

Keywords

  • Data Mining: DM: Recommender systems
  • Machine Learning: ML: Causality

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.

Zhirong Huang, Debo Cheng, Lin Liu, Jiuyong Li, Guangquan Lu, and Shichao Zhang. 2025. Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 2955–2963. https://doi.org/10.24963/ijcai.2025/329
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards