Counteracting User Attention Bias in Music Streaming Recommendation via Reward Modification
Authors:
Open Access
- 14 August 2022
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2504-2514
Abstract
In streaming media applications, like music Apps, songs are recommended in a continuous way in users' daily life. The recommended songs are played automatically although users may not pay any attention to them, posing a challenge of user attention bias in training recommendation models, i.e., the training instances contain a large number of false-positive labels (users' feedback). Existing approaches either directly use the auto-feedbacks or heuristically delete the potential false-positive labels. Both of the approaches lead to biased results because the false-positive labels cause the shift of training data distribution, hurting the accuracy of the recommendation models. In this paper, we propose a learning-based counterfactual approach to adjusting the user auto-feedbacks and learning the recommendation models using Neural Dueling Bandit algorithm, called NDB. Specifically, NDB maintains two neural networks: a user attention network for computing the importance weights that are used for modifying the original rewards, and another random network trained with dueling bandit for conducting online recommendations based on the modified rewards. Theoretical analysis showed that the modified rewards are statistically unbiased, and the learned bandit policy enjoys a sub-linear regret bound. Experimental results demonstrated that NDB can significantly outperform the state-of-the-art baselines.Keywords
Funding Information
- National Natural Science Foundation of China (62006234 61872338 61832017)
- Major Innovation & Planning Interdisciplinary Platform for the ``Double-First Class' Initiative Renmin University of China
- the Fundamental Research Funds for the Central Universities and the Research Funds of Renmin University of China (No.22XNH027)
- Beijing Outstanding Young Scientist Program (NO. BJJWZYJH012019100020098)
- Intelligent Social Governance Interdisciplinary Platform
- Public Policy and Decision-making Research Lab of Renmin University of China
- National Key R&D Program of China (2019YFE0198200)
This publication has 21 references indexed in Scilit:
- Attentive neural architecture incorporating song features for music recommendation2018
- Explicit Modelling of the Implicit Short Term User Preferences for Music Recommendation2018
- Understanding Music Listening Intents During Daily Activities with Implications for Contextual Music Recommendation2018
- Personality-Based User Modeling for Music Recommender Systems2016
- On-demand streaming services and music industry revenues — Insights from Spotify's market entryInternational Journal of Research in Marketing, 2016
- Multileave Gradient Descent for Fast Online Learning to Rank2016
- Automated Generation of Music Playlists: Survey and ExperimentsACM Computing Surveys, 2014
- Understanding user behavior in Spotify2013
- A contextual-bandit approach to personalized news article recommendation2010
- Interactively optimizing information retrieval systems as a dueling bandits problem2009