DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias

Abstract

Recommender systems are prone to be misled by biases in the data. Models trained with biased data fail to capture the real interests of users, thus it is critical to alleviate the impact of bias to achieve unbiased recommendation. In this work, we focus on an essential bias in micro-video recommendation, duration bias. Specifically, existing micro-video recommender systems usually consider watch time as the most critical metric, which measures how long a user watches a video. Since videos with longer duration tend to have longer watch time, there exists a kind of duration bias, making longer videos tend to be recommended more against short videos. In this paper, we empirically show that commonly-used metrics are vulnerable to duration bias, making them NOT suitable for evaluating micro-video recommendation. To address it, we further propose an unbiased evaluation metric, called WTG (short for Watch Time Gain). Empirical results reveal that WTG can alleviate duration bias and better measure recommendation performance. Moreover, we design a simple yet effective model named DVR (short for Debiased Video Recommendation) that can provide unbiased recommendation of micro-videos with varying duration, and learn unbiased user preferences via adversarial learning. Extensive experiments based on two real-world datasets demonstrate that DVR successfully eliminates duration bias and significantly improves recommendation performance with over 30% relative progress. Codes and datasets are released at https://github.com/tsinghua-fib-lab/WTG-DVR.

arXiv commentAccepted by MM'22

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• TensorFlow: A system for large-scale machine learning
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• Unsupervised Domain Adaptation by Backpropagation
• AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks
• Causal Intervention for Leveraging Popularity Bias in Recommendation
• Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations
• User-oriented Fairness in Recommendation
• Bias and Debias in Recommender System: A Survey and Future Directions
• Personalized Counterfactual Fairness in Recommendation
• Offline A/B testing for Recommender Systems
• DGCN: Diversified Recommendation with Graph Convolutional Networks
• Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction
• User Fairness in Recommender Systems
• AutoFIS: Automatic Feature Interaction Selection in Factorization Models for Click-Through Rate Prediction
• TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providers

Cited by in corpus (7)

• Uncovering User Interest from Biased and Noised Watch Time in Video Recommendation
• Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework
• LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting
• Learning and Optimization of Implicit Negative Feedback for Industrial Short-video Recommender System
• Describe What You See with Multimodal Large Language Models to Enhance Video Recommendations
• Not All Videos Become Outdated: Short-Video Recommendation by Learning to Deconfound Release Interval Bias
• Mend the Measurement Gap: Latent User Preference Modeling for Short-Form Video Recommendation