LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting
arXiv:2312.10947 · doi:10.1145/3616855.3635816
Abstract
Short video recommendations often face limitations due to the quality of user feedback, which may not accurately depict user interests. To tackle this challenge, a new task has emerged: generating more dependable labels from original feedback. Existing label generation methods rely on manual rules, demanding substantial human effort and potentially misaligning with the desired objectives of the platform. To transcend these constraints, we introduce LabelCraft, a novel automated label generation method explicitly optimizing pivotal operational metrics for platform success. By formulating label generation as a higher-level optimization problem above recommender model optimization, LabelCraft introduces a trainable labeling model for automatic label mechanism modeling. Through meta-learning techniques, LabelCraft effectively addresses the bi-level optimization hurdle posed by the recommender and labeling models, enabling the automatic acquisition of intricate label generation mechanisms. Extensive experiments on real-world datasets corroborate LabelCraft's excellence across varied operational metrics, encompassing usage time, user engagement, and retention. Codes are available at https://github.com/baiyimeng/LabelCraft.
Accepted by WSDM'24
References in corpus (10)
- TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendation
- Deconfounded Recommendation for Alleviating Bias Amplification
- User-controllable Recommendation Against Filter Bubbles
- Multi-Task Fusion via Reinforcement Learning for Long-Term User Satisfaction in Recommender Systems
- Balancing Unobserved Confounding with a Few Unbiased Ratings in Debiased Recommendations
- DVR: Micro-Video Recommendation Optimizing Watch-Time-Gain under Duration Bias
- Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework
- Generative Flow Network for Listwise Recommendation
- ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor
- CoLLM: Integrating Collaborative Embeddings into Large Language Models for Recommendation