On the Consistency of Average Embeddings for Item Recommendation
This addresses a common practice in recommender systems for users like developers, but it is incremental as it focuses on analyzing an existing method.
The paper investigated the relevance of averaging item embeddings for recommendation by proposing an expected precision score to measure consistency, finding that real-world averages are less consistent for recommendation.
A prevalent practice in recommender systems consists in averaging item embeddings to represent users or higher-level concepts in the same embedding space. This paper investigates the relevance of such a practice. For this purpose, we propose an expected precision score, designed to measure the consistency of an average embedding relative to the items used for its construction. We subsequently analyze the mathematical expression of this score in a theoretical setting with specific assumptions, as well as its empirical behavior on real-world data from music streaming services. Our results emphasize that real-world averages are less consistent for recommendation, which paves the way for future research to better align real-world embeddings with assumptions from our theoretical setting.