Cold-start Recommendation by Personalized Embedding Region Elicitation

TL;DR

This paper introduces a personalized, two-phase rating elicitation method for cold-start recommender systems that models user preferences as regions in embedding space, improving recommendation accuracy for new users.

Contribution

It proposes a novel 2-phase, region-based user preference elicitation scheme that adaptively refines user embeddings, outperforming fixed seed set methods.

Findings

Effective in cold-start scenarios with no prior user data

Outperforms existing rating-elicitation methods on multiple datasets

Efficient implementation of each subproblem in the scheme

Abstract

Rating elicitation is a success element for recommender systems to perform well at cold-starting, in which the systems need to recommend items to a newly arrived user with no prior knowledge about the user's preference. Existing elicitation methods employ a fixed set of items to learn the user's preference and then infer the users' preferences on the remaining items. Using a fixed seed set can limit the performance of the recommendation system since the seed set is unlikely optimal for all new users with potentially diverse preferences. This paper addresses this challenge using a 2-phase, personalized elicitation scheme. First, the elicitation scheme asks users to rate a small set of popular items in a ``burn-in'' phase. Second, it sequentially asks the user to rate adaptive items to refine the preference and the user's representation. Throughout the process, the system represents the user's embedding value not by a point estimate but by a region estimate. The value of information obtained by asking the user's rating on an item is quantified by the distance from the region center embedding space that contains with high confidence the true embedding value of the user. Finally, the recommendations are successively generated by considering the preference region of the user. We show that each subproblem in the elicitation scheme can be efficiently implemented. Further, we empirically demonstrate the effectiveness of the proposed method against existing rating-elicitation methods on several prominent datasets.