Why Not Together? A Multiple-Round Recommender System for Queries and Items

A fundamental technique of recommender systems involves modeling user preferences, where queries and items are widely used as symbolic representations of user interests. Queries delineate user needs at an abstract level, providing a high-level description, whereas items operate on a more specific and concrete level, representing the granular facets of user preference. While practical, both query and item recommendations encounter the challenge of sparse user feedback. To this end, we propose a novel approach named Multiple-round Auto Guess-and-Update System (MAGUS) that capitalizes on the synergies between both types, allowing us to leverage both query and item information to form user interests. This integrated system introduces a recursive framework that could be applied to any recommendation method to exploit queries and items in historical interactions and to provide recommendations for both queries and items in each interaction round. Concretely, MAGUS first represents queries and items through combinations of categorical words, and then constructs a relational graph to capture the interconnections and dependencies among these individual words and word combinations. In response to each user request, MAGUS employs an offline tuned recommendation model to assign estimated scores to words representing items; and these scores are subsequently disseminated throughout the graph, impacting each individual word or combination of words. Through multiple-round interactions, MAGUS initially guesses user interests by formulating meaningful word combinations and presenting them as potential queries or items. Subsequently, MAGUS is updated based on user feedback, enhancing its recommendations iteratively. Empirical results from testing 12 different recommendation methods demonstrate that integrating queries into item recommendations via MA-GUS significantly enhances the efficiency, with which users can identify their preferred items during multiple-round interactions.