# Semantic IDs for Music Recommendation

arXiv: https://arxiv.org/abs/2507.18800 · HTML: https://mlsanity.com/paper/2507.18800/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 18 references that are in the map.
- First posted on arXiv 24 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Compositional Embeddings Using Complementary Partitions for Memory-Efficient Recommendation Systems](https://mlsanity.com/paper/1909.02107/) (2019)
- [Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations](https://mlsanity.com/paper/2306.08121/) (2023)
- [Learning Multi-granular Quantized Embeddings for Large-Vocab Categorical Features in Recommender Systems](https://mlsanity.com/paper/2002.08530/) (2020)
- [Widespread Flaws in Offline Evaluation of Recommender Systems](https://mlsanity.com/paper/2307.14951/) (2023)
- [The Music Streaming Sessions Dataset](https://mlsanity.com/paper/1901.09851/) (2018)
- [Scaling Session-Based Transformer Recommendations using Optimized Negative Sampling and Loss Functions](https://mlsanity.com/paper/2307.14906/) (2023)
- [RecJPQ: Training Large-Catalogue Sequential Recommenders](https://mlsanity.com/paper/2312.06165/) (2023)

## Abstract (arXiv)

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.