Self-supervised Learning for Large-scale Item Recommendations
2021pp. 4321–4330
Citations Over TimeTop 1% of 2021 papers
Tiansheng Yao, Xinyang Yi, Derek Zhiyuan Cheng, Felix Yu, Ting Chen, Aditya Krishna Menon, Lichan Hong, Ed H., Steve Tjoa, Jieqi Kang, Evan Ettinger
Abstract
Large scale recommender models find most relevant items from huge catalogs, and they play a critical role in modern search and recommendation systems. To model the input space with large-vocab categorical features, a typical recommender model learns a joint embedding space through neural networks for both queries and items from user feedback data. However, with millions to billions of items in the corpus, users tend to provide feedback for a very small set of them, causing a power-law distribution. This makes the feedback data for long-tail items extremely sparse.
Related Papers
- → Design of Garment Style Recommendation System Based on Interactive Genetic Algorithm(2022)8 cited
- → Weighted hybrid technique for recommender system(2017)18 cited
- → Comparing Pre-filtering and Post-filtering Approach in a Collaborative Contextual Recommender System: An Application to E-Commerce(2009)13 cited
- → Facebook Based Choice Filtering(2017)5 cited
- → Collaborative Filtering based simple restaurant recommender(2014)3 cited