Practical Linear Models for Large-Scale One-Class Collaborative Filtering

Collaborative filtering has emerged as the de facto approach to personalized recommendation problems. However, a scenario that has proven difficult in practice is the one-class collaborative filtering case (OC-CF), where one has examples of items that a user prefers, but no examples of items they do not prefer. In such cases, it is desirable to have recommendation algorithms that are personalized, learning-based, and highly scalable. Existing linear recommenders for OC-CF achieve good performance in benchmarking tasks, but they involve solving a large number of a regression subproblems, limiting their applicability to large-scale problems. We show that it is possible to scale up linear recommenders to big data by learning an OC-CF model in a randomized low-dimensional embedding of the user-item interaction matrix. Our algorithm, Linear-FLow, achieves state-of-the-art performance in a comprehensive set of experiments on standard benchmarks as well as real data.

Authors

• Suvash Sedhain
• Hung Bui
• Jaya Kawale
• Nikos Vlassis Adobe Research
• Branislav Kveton Adobe Research
• Aditya Krishna Menon
• Trung Bui
• Scott Sanner Department of Mechanical and Industrial Engineering, University of Toronto Vector Institute for AI

Keywords

No keywords are indexed for this paper.