Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices

• URL: http://arxiv.org/abs/2604.03949v1
• Date: Sun, 05 Apr 2026 03:46:52 GMT
• Title: Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices
• Abstract summary: We discuss practical technical challenges we encountered while applying Semantic IDs (SIDs) at Snapchat.<n>SIDs have drastically smaller cardinality than the atomic counterpart, and induce semantic clustering in the ID space.<n>We apply SIDs as auxiliary features for ranking models, and also explore SIDs as additional retrieval sources in different ML applications.
• Score: 39.95009019603262
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Effective item identifiers (IDs) are an important component for recommender systems (RecSys) in practice, and are commonly adopted in many use cases such as retrieval and ranking. IDs can encode collaborative filtering signals within training data, such that RecSys models can extrapolate during the inference and personalize the prediction based on users' behavioral histories. Recently, Semantic IDs (SIDs) have become a trending paradigm for RecSys. In comparison to the conventional atomic ID, an SID is an ordered list of codes, derived from tokenizers such as residual quantization, applied to semantic representations commonly extracted from foundation models or collaborative signals. SIDs have drastically smaller cardinality than the atomic counterpart, and induce semantic clustering in the ID space. At Snapchat, we apply SIDs as auxiliary features for ranking models, and also explore SIDs as additional retrieval sources in different ML applications. In this paper, we discuss practical technical challenges we encountered while applying SIDs, experiments we have conducted, and design choices we have iterated to mitigate these challenges. Backed by promising offline results on both internal data and academic benchmarks as well as online A/B studies, SID variants have been launched in multiple production models with positive metrics impact.

Related papers

• DREAM: Dynamic Refinement of Early Assignment Mappings [7.781421530363403]
  Current methods assign each item a single static identifier through offline tokenization before sufficient user feedback is observed.<n>We identify this one-shot commitment as the fundamental cold-start bottleneck in SID-based generative recommendation.<n>We propose DREAM, a three-stage framework that resolves this flaw through progressive refinement.
  arXiv  Detail & Related papers  (2026-06-05T06:21:01Z)
• DSIRM: Learning Query-Bridged Discrete Semantic Identifiers for E-commerce Relevance Modeling [3.0848956918142605]
  We present a query-bridged contrastive quantization approach on the item side, injecting query-item interaction supervision into Hierarchical Quantization.<n>On the other hand, we explore generative LLMs on the query side to explicitly predict item SIDs from text.<n>Our proposed approach has achieved better results, improving offline AUC by +1.54%.
  arXiv  Detail & Related papers  (2026-06-03T02:42:52Z)
• SID-Coord: Coordinating Semantic IDs for ID-based Ranking in Short-Video Search [9.72713305999446]
  We propose SID-Coord, a lightweight Semantic ID framework that incorporates discrete, trainable semantic IDs directly into ID-based ranking models.<n>Instead of treating semantic signals as auxiliary dense features, SID-Coord represents semantics as structured identifiers.<n>Online A/B experiments in a real-world production environment show statistically significant improvements.
  arXiv  Detail & Related papers  (2026-04-12T05:51:35Z)
• Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs [17.944727019161878]
  ReSID is a principled, SID framework that recommend learning from the perspective of information preservation and sequential predictability.<n>It consistently outperforms strong sequential and SID-based generative baselines by an average of over 10%, while reducing tokenization cost by up to 122x.
  arXiv  Detail & Related papers  (2026-02-02T17:00:04Z)
• Differentiable Semantic ID for Generative Recommendation [65.83703273297492]
  Generative recommendation provides a novel paradigm in which each item is represented by a discrete semantic ID (SID) learned from rich content.<n>In practice, SIDs are typically optimized only for content reconstruction rather than recommendation accuracy.<n>A natural approach is to make semantic indexing differentiable so that recommendation gradients can directly influence SID learning.<n>We propose DIGER, a first step toward effective differentiable semantic IDs for generative recommendation.
  arXiv  Detail & Related papers  (2026-01-27T15:34:11Z)
• The Best of the Two Worlds: Harmonizing Semantic and Hash IDs for Sequential Recommendation [51.62815306481903]
  We propose textbfname, a novel framework that harmonizes the SID and HID. Specifically, we devise a dual-branch modeling architecture that enables the model to capture both the multi-granular semantics within SID while preserving the unique collaborative identity of HID.<n>Experiments on three real-world datasets show that name balances recommendation quality for both head and tail items while surpassing the existing baselines.
  arXiv  Detail & Related papers  (2025-12-11T07:50:53Z)
• Enhancing Embedding Representation Stability in Recommendation Systems with Semantic ID [29.560370412849874]
  This paper introduces Semantic ID prefix ngram, a novel token parameterization technique that significantly improves the performance of the original Semantic ID.<n>We show that Semantic ID prefix ngram not only addresses embedding instability but also significantly improves tail id modeling, reduces overfitting, and mitigates representation shifts.<n>We also report our experience of integrating Semantic ID into Meta production Ads Ranking system, leading to notable performance gains and enhanced prediction stability in live deployments.
  arXiv  Detail & Related papers  (2025-04-02T21:28:38Z)
• Order-agnostic Identifier for Large Language Model-based Generative Recommendation [94.37662915542603]
  Items are assigned identifiers for Large Language Models (LLMs) to encode user history and generate the next item.<n>Existing approaches leverage either token-sequence identifiers, representing items as discrete token sequences, or single-token identifiers, using ID or semantic embeddings.<n>We propose SETRec, which leverages semantic tokenizers to obtain order-agnostic multi-dimensional tokens.
  arXiv  Detail & Related papers  (2025-02-15T15:25:38Z)
• ASI++: Towards Distributionally Balanced End-to-End Generative Retrieval [29.65717446547002]
  ASI++ is a novel fully end-to-end generative retrieval method. It aims to simultaneously learn balanced ID assignments and improve retrieval performance.
  arXiv  Detail & Related papers  (2024-05-23T07:54:57Z)
• Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations [24.952222114424146]
  We propose using content-derived features as a replacement for random ids. We show that simply replacing ID features with content-based embeddings can cause a drop in quality due to reduced memorization capability. Similar to content embeddings, the compactness of Semantic IDs poses a problem of easy adaption in recommendation models.
  arXiv  Detail & Related papers  (2023-06-13T20:34:15Z)
• Recommender Systems with Generative Retrieval [58.454606442670034]
  We propose a novel generative retrieval approach, where the retrieval model autoregressively decodes the identifiers of the target candidates. To that end, we create semantically meaningful of codewords to serve as a Semantic ID for each item. We show that recommender systems trained with the proposed paradigm significantly outperform the current SOTA models on various datasets.
  arXiv  Detail & Related papers  (2023-05-08T21:48:17Z)
• CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions [61.724894233252414]
  This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem. Existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering. We introduce a different unsupervised method that allows us to learn pedestrian embeddings from raw videos, without resorting to pseudo labels.
  arXiv  Detail & Related papers  (2020-07-15T09:52:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.