English

Semantic IDs for Music Recommendation

Information Retrieval 2025-07-28 v1 Machine Learning

Abstract

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.

Keywords

Cite

@article{arxiv.2507.18800,
  title  = {Semantic IDs for Music Recommendation},
  author = {M. Jeffrey Mei and Florian Henkel and Samuel E. Sandberg and Oliver Bembom and Andreas F. Ehmann},
  journal= {arXiv preprint arXiv:2507.18800},
  year   = {2025}
}

Comments

RecSys 2025 Industry Track

R2 v1 2026-07-01T04:17:53.382Z