Bias and Debias in Recommender System: A Survey and Future Directions

Abstract

While recent years have witnessed a rapid growth of research papers on recommender system (RS), most of the papers focus on inventing machine learning models to better fit user behavior data. However, user behavior data is observational rather than experimental. This makes various biases widely exist in the data, including but not limited to selection bias, position bias, exposure bias, and popularity bias. Blindly fitting the data without considering the inherent biases will result in many serious issues, e.g., the discrepancy between offline evaluation and online metrics, hurting user satisfaction and trust on the recommendation service, etc. To transform the large volume of research models into practical improvements, it is highly urgent to explore the impacts of the biases and perform debiasing when necessary. When reviewing the papers that consider biases in RS, we find that, to our surprise, the studies are rather fragmented and lack a systematic organization. The terminology ``bias'' is widely used in the literature, but its definition is usually vague and even inconsistent across papers. This motivates us to provide a systematic survey of existing work on RS biases. In this paper, we first summarize seven types of biases in recommendation, along with their definitions and characteristics. We then provide a taxonomy to position and organize the existing work on recommendation debiasing. Finally, we identify some open challenges and envision some future directions, with the hope of inspiring more research work on this important yet less investigated topic. The summary of debiasing methods reviewed in this survey can be found at \url{https://github.com/jiawei-chen/RecDebiasing}.

A new version of the bias survey, with supplementing causal explanations of biases and the latest debiasing technologies

Cited by in corpus (34)

• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• Causal Intervention for Leveraging Popularity Bias in Recommendation
• A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation
• A Survey on the Fairness of Recommender Systems
• KuaiRec: A Fully-observed Dataset and Insights for Evaluating Recommender Systems
• Large Language Models as Zero-Shot Conversational Recommenders
• KuaiRand: An Unbiased Sequential Recommendation Dataset with Randomly Exposed Videos
• SAR-Net: A Scenario-Aware Ranking Network for Personalized Fair Recommendation in Hundreds of Travel Scenarios
• A Graph-based Approach for Mitigating Multi-sided Exposure Bias in Recommender Systems
• Should Graph Convolution Trust Neighbors? A Simple Causal Inference Method
• Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation
• Graph Masked Autoencoder for Sequential Recommendation
• CausPref: Causal Preference Learning for Out-of-Distribution Recommendation
• Unbiased Knowledge Distillation for Recommendation
• Evolutionary Preference Learning via Graph Nested GRU ODE for Session-based Recommendation
• Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations
• On the Theories Behind Hard Negative Sampling for Recommendation
• It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences Are Dynamic
• Debiasing Learning for Membership Inference Attacks Against Recommender Systems
• Improving Implicit Feedback-Based Recommendation through Multi-Behavior Alignment
• DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias
• Robust Collaborative Filtering to Popularity Distribution Shift
• A Comparative Analysis of Bias Amplification in Graph Neural Network Approaches for Recommender Systems
• User Consented Federated Recommender System Against Personalized Attribute Inference Attack
• Deep Generative Imputation Model for Missing Not At Random Data
• Pareto Invariant Representation Learning for Multimedia Recommendation
• Debiasing Sequential Recommenders through Distributionally Robust Optimization over System Exposure
• Debiasing the Cloze Task in Sequential Recommendation with Bidirectional Transformers
• Capturing Popularity Trends: A Simplistic Non-Personalized Approach for Enhanced Item Recommendation
• Curse of "Low" Dimensionality in Recommender Systems
• Unbiased Learning to Rank with Biased Continuous Feedback
• Unbiased Pairwise Learning from Implicit Feedback for Recommender Systems without Biased Variance Control
• A General Framework for Pairwise Unbiased Learning to Rank
• Pure Spectral Graph Embeddings: Reinterpreting Graph Convolution for Top-N Recommendation