Interaction-Data-guided Conditional Instrumental Variables for Debiasing Recommender Systems
This work addresses bias mitigation in recommender systems, which is an incremental improvement for enhancing fairness and accuracy in personalized recommendations.
The paper tackles the challenge of identifying valid instrumental variables to address confounding bias in recommender systems by proposing IDCIV-RS, which automatically generates conditional IV representations from interaction data using a VAE and least squares, resulting in improved recommendation accuracy on datasets like Movielens-10M and Douban-Movie.
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.