CDR: Conservative Doubly Robust Learning for Debiased Recommendation

2023/08/13 by ZiJie Song, Jiawei Chen, Song, ZiJie +11 · 2 citations
Computer Science · #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Face and Expression Recognition #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Machine Learning and ELM

paper · pdf · doi:10.48550/arxiv.2308.08461

openalex publication_date 2023/08/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• DUET: Dual Model Co-Training for Entire Space CTR Prediction
• BPL: Bias-adaptive Preference Distillation Learning for Recommender System

Related

• StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random
• TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased Recommendations
• Multiple Robust Learning for Recommendation
• Recommendations as Treatments: Debiasing Learning and Evaluation
• Debiased Recommendation with Noisy Feedback