Saved in:
Bibliographic Details
Main Authors: Mei, M. Jeffrey, Henkel, Florian, Sandberg, Samuel E., Bembom, Oliver, Ehmann, Andreas F.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2507.18800
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Training recommender systems for next-item recommendation often requires unique embeddings to be learned for each item, which may take up most of the trainable parameters for a model. Shared embeddings, such as using content information, can reduce the number of distinct embeddings to be stored in memory. This allows for a more lightweight model; correspondingly, model complexity can be increased due to having fewer embeddings to store in memory. We show the benefit of using shared content-based features ('semantic IDs') in improving recommendation accuracy and diversity, while reducing model size, for two music recommendation datasets, including an online A/B test on a music streaming service.