# SIDE: Semantic ID Embedding for effective learning from sequences

arXiv: https://arxiv.org/abs/2506.16698 · HTML: https://mlsanity.com/paper/2506.16698/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 14 references that are in the map.
- First posted on arXiv 20 Jun 2025.

## Builds on (most cited first, 8 of 8)

- [Autoregressive Image Generation using Residual Quantization](https://mlsanity.com/paper/2203.01941/) (2022)
- [Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation](https://mlsanity.com/paper/2310.05737/) (2023)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [Deep Learning Recommendation Model for Personalization and Recommendation Systems](https://mlsanity.com/paper/1906.00091/) (2019)
- [The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits](https://mlsanity.com/paper/2402.17764/) (2024)
- [Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Prediction](https://mlsanity.com/paper/2006.05639/) (2020)
- [Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks](https://mlsanity.com/paper/1810.00825/) (2018)
- [Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations](https://mlsanity.com/paper/2306.08121/) (2023)

## Built on by (most cited first, 3 of 3)

- [COFFEE: COdesign Framework for Feature Enriched Embeddings in Ads-Ranking Systems](https://mlsanity.com/paper/2601.02807/) (2026)
- [DynamiX: Dynamic Resource eXploration for Personalized Ad-Recommendations](https://mlsanity.com/paper/2511.18331/) (2025)
- [DUET -- Dual User Embedding Transformers for Offsite Conversion Prediction](https://mlsanity.com/paper/2606.10243/) (2026)

## Abstract (arXiv)

Sequence-based recommendations models are driving the state-of-the-art for industrial ad-recommendation systems. Such systems typically deal with user histories or sequence lengths ranging in the order of O(10^3) to O(10^4) events. While adding embeddings at this scale is manageable in pre-trained models, incorporating them into real-time prediction models is challenging due to both storage and inference costs. To address this scaling challenge, we propose a novel approach that leverages vector quantization (VQ) to inject a compact Semantic ID (SID) as input to the recommendation models instead of a collection of embeddings. Our method builds on recent works of SIDs by introducing three key innovations: (i) a multi-task VQ-VAE framework, called VQ fusion that fuses multiple content embeddings and categorical predictions into a single Semantic ID; (ii) a parameter-free, highly granular SID-to-embedding conversion technique, called SIDE, that is validated with two content embedding collections, thereby eliminating the need for a large parameterized lookup table; and (iii) a novel quantization method called Discrete-PCA (DPCA) which generalizes and enhances residual quantization techniques. The proposed enhancements when applied to a large-scale industrial ads-recommendation system achieves 2.4X improvement in normalized entropy (NE) gain and 3X reduction in data footprint compared to traditional SID methods.