The Sample Complexity of Online One-Class Collaborative Filtering

We consider the online one-class collaborative filtering (CF) problem that consists of recommending items to users over time in an online fashion based on positive ratings only. This problem arises when users respond only occasionally to a recommendation with a positive rating, and never with a negative one. We study the impact of the probability of a user responding to a recommendation, p_f, on the sample complexity, i.e., the number of ratings required to make `good' recommendations, and ask whether receiving positive and negative ratings, instead of positive ratings only, improves the sample complexity. Both questions arise in the design of recommender systems. We introduce a simple probabilistic user model, and analyze the performance of an online user-based CF algorithm. We prove that after an initial cold start phase, where recommendations are invested in exploring the user's preferences, this algorithm makes---up to a fraction of the recommendations required for updating the user's preferences---perfect recommendations. The number of ratings required for the cold start phase is nearly proportional to 1/p_f, and that for updating the user's preferences is essentially independent of p_f. As a consequence we find that, receiving positive and negative ratings instead of only positive ones improves the number of ratings required for initial exploration by a factor of 1/p_f, which can be significant.

[1]  Zheng Wen,et al.  Cascading Bandits: Learning to Rank in the Cascade Model , 2015, ICML.

[2]  Onkar Dabeer,et al.  Analysis of a Collaborative Filter Based on Popularity Amongst Neighbors , 2012, IEEE Transactions on Information Theory.

[3]  John Riedl,et al.  Analysis of recommendation algorithms for e-commerce , 2000, EC '00.

[4]  Devavrat Shah,et al.  Regret Guarantees for Item-Item Collaborative Filtering , 2015 .

[5]  Benoit Cadre,et al.  Statistical analysis of $k$-nearest neighbor collaborative recommendation , 2010 .

[6]  Mehrbakhsh Nilashi,et al.  Collaborative filtering recommender systems , 2013 .

[7]  Andrea Montanari,et al.  Linear bandits in high dimension and recommendation systems , 2012, 2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[8]  Yifan Hu,et al.  Collaborative Filtering for Implicit Feedback Datasets , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[9]  Reinhard Heckel,et al.  Scalable and Interpretable Product Recommendations via Overlapping Co-Clustering , 2016, 2017 IEEE 33rd International Conference on Data Engineering (ICDE).

[10]  Deepayan Chakrabarti,et al.  Multi-armed bandit problems with dependent arms , 2007, ICML '07.

[11]  Sébastien Bubeck,et al.  Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems , 2012, Found. Trends Mach. Learn..

[12]  Odalric-Ambrym Maillard,et al.  Concentration inequalities for sampling without replacement , 2013, 1309.4029.

[13]  Qiang Yang,et al.  One-Class Collaborative Filtering , 2008, 2008 Eighth IEEE International Conference on Data Mining.

[14]  Onkar Dabeer.  Adaptive collaborating filtering: The low noise regime , 2013, 2013 IEEE International Symposium on Information Theory.

[15]  Devavrat Shah,et al.  A Latent Source Model for Online Collaborative Filtering , 2014, NIPS.

[16]  F. Maxwell Harper,et al.  The MovieLens Datasets: History and Context , 2016, TIIS.

[17]  Charu C. Aggarwal,et al.  Recommender Systems: The Textbook , 2016 .