CDR: Conservative Doubly Robust Learning for Debiased Recommendation
This work addresses bias in recommendation systems, which is a critical issue for improving user experience and fairness, but it appears incremental as it builds on existing Doubly Robust Learning methods.
The paper tackles the problem of bias in recommendation systems by addressing 'Poisonous Imputation' in Doubly Robust Learning methods, proposing a Conservative Doubly Robust strategy that filters imputations based on mean and variance, resulting in significant performance enhancements and reduced frequency of poisonous imputation.
In recommendation systems (RS), user behavior data is observational rather than experimental, resulting in widespread bias in the data. Consequently, tackling bias has emerged as a major challenge in the field of recommendation systems. Recently, Doubly Robust Learning (DR) has gained significant attention due to its remarkable performance and robust properties. However, our experimental findings indicate that existing DR methods are severely impacted by the presence of so-called Poisonous Imputation, where the imputation significantly deviates from the truth and becomes counterproductive. To address this issue, this work proposes Conservative Doubly Robust strategy (CDR) which filters imputations by scrutinizing their mean and variance. Theoretical analyses show that CDR offers reduced variance and improved tail bounds.In addition, our experimental investigations illustrate that CDR significantly enhances performance and can indeed reduce the frequency of poisonous imputation.