Mitigating Collaborative Semantic ID Staleness in Generative Retrieval

• URL: http://arxiv.org/abs/2604.13273v1
• Date: Tue, 14 Apr 2026 20:06:48 GMT
• Title: Mitigating Collaborative Semantic ID Staleness in Generative Retrieval
• Abstract summary: Generative retrieval with Semantic IDs (SIDs) assigns each item a discrete identifier and treats retrieval as a sequence generation problem.<n>As interaction patterns drift over time, SIDs become stale, i.e., their collaborative semantics no longer match recent logs.<n>We propose a lightweight, model-agnostic SID alignment update.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative retrieval with Semantic IDs (SIDs) assigns each item a discrete identifier and treats retrieval as a sequence generation problem rather than a nearest-neighbor search. While content-only SIDs are stable, they do not take into account user-item interaction patterns, so recent systems construct interaction-informed SIDs. However, as interaction patterns drift over time, these identifiers become stale, i.e., their collaborative semantics no longer match recent logs. Prior work typically assumes a fixed SID vocabulary during fine-tuning, or treats SID refresh as a full rebuild that requires retraining. However, SID staleness under temporal drift is rarely analyzed explicitly. To bridge this gap, we study SID staleness under strict chronological evaluation and propose a lightweight, model-agnostic SID alignment update. Given refreshed SIDs derived from recent logs, we align them to the existing SID vocabulary so the retriever checkpoint remains compatible, enabling standard warm-start fine-tuning without a full rebuild-and-retrain pipeline. Across three public benchmarks, our update consistently improves Recall@K and nDCG@K at high cutoffs over naive fine-tuning with stale SIDs and reduces retriever-training compute by approximately 8-9 times compared to full retraining.

Related papers

• Restoring Collaborative Signals in Semantic-ID Generative Recommendation via Personalized Natural Language [14.28332940068789]
  LLM-based generative recommendation models cast recommendation as autoregressively generating an item's semantic-ID (SID)<n>This setting verbalizes the model's knowledge poorly, and text and SID tokens live in misaligned embedding spaces.<n>We propose a framework, guided by personalized natural language, that adds hierarchical collaborative cues as the model generates.
  arXiv  Detail & Related papers  (2026-07-30T04:58:22Z)
• CogRec: Structure-Cognitive Fast-and-Slow Reasoning for Generative Recommendation [29.663400191042996]
  CogRec is a structure-cognitive fast-and-slow reasoning framework.<n>CogRec augments the vertical SID hierarchy with intra-layer semantic graphs and item-level neighborhoods.<n> SID Routing represents recommendation reasoning through layer-wise Match, LateralJump, and Explore operations.
  arXiv  Detail & Related papers  (2026-07-27T13:19:55Z)
• Can Generative Recommendation Reach Cold Items? A Temporal Perspective on Semantic-ID Generation [19.158930665677]
  We show that SID-based models can occasionally reach future items supported by observed tokens and prefixes, but struggle with unseen atomic tokens and unsupported SID paths.<n>These findings show that SID generation is compositional but not fully open-ended, and suggest future directions in more independent SID spaces.
  arXiv  Detail & Related papers  (2026-07-23T09:30:49Z)
• 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)
• FRESCO: Benchmarking and Optimizing Re-rankers for Evolving Semantic Conflict in Retrieval-Augmented Generation [73.22935457705057]
  We introduce FRESCO, a benchmark for evaluating re-rankers in temporally dynamic contexts.<n>By pairing recency-seeking queries with historical Wikipedia revisions, FRESCO tests whether re-rankers can prioritize factually recent evidence while maintaining semantic relevance.<n>Our evaluation reveals a consistent failure mode across existing re-rankers: a strong bias toward older, semantically rich documents, even when they are factually obsolete.
  arXiv  Detail & Related papers  (2026-04-14T17:04:25Z)
• 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)
• Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices [39.95009019603262]
  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.
  arXiv  Detail & Related papers  (2026-04-05T03:46:52Z)
• IntRR: A Framework for Integrating SID Redistribution and Length Reduction [14.327886721362647]
  We propose IntRR, a novel framework that integrates objective-aligned SID Redistribution and structural Length Reduction.<n>IntRR yields substantial improvements over representative generative baselines, achieving superior performance in both recommendation accuracy and efficiency.
  arXiv  Detail & Related papers  (2026-02-24T09:09:40Z)
• End-to-End Semantic ID Generation for Generative Advertisement Recommendation [33.453121305193434]
  We propose a Unified SID generation framework for generative advertisement recommendation.<n>Specifically, we jointly optimize embeddings and SIDs in an end-to-end manner from raw advertising data.<n>Experiments demonstrate that UniSID consistently outperforms state-of-the-art SID generation methods.
  arXiv  Detail & Related papers  (2026-02-11T02:38:26Z)
• GLASS: A Generative Recommender for Long-sequence Modeling via SID-Tier and Semantic Search [51.44490997013772]
  GLASS is a novel framework that integrates long-term user interests into the generative process via SID-Tier and Semantic Search.<n>We show that GLASS outperforms state-of-the-art baselines in experiments on two large-scale real-world datasets.
  arXiv  Detail & Related papers  (2026-02-05T13:48:33Z)
• 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)
• Bi-C2R: Bidirectional Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification [77.07028925223383]
  Lifelong person Re-IDentification (L-ReID) exploits sequentially collected data to continuously train and update a ReID model.<n>Existing L-ReID methods typically re-extract new features for all historical gallery images for inference after each update, known as "re-indexing"<n>This paper focuses on a new task called Re-index Free Lifelong person Re-IDentification (RFL-ReID), which requires performing lifelong person re-identification without re-indexing historical gallery images.
  arXiv  Detail & Related papers  (2025-12-31T17:50:05Z)
• 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)
• DSI++: Updating Transformer Memory with New Documents [95.70264288158766]
  We introduce DSI++, a continual learning challenge for DSI to incrementally index new documents. We show that continual indexing of new documents leads to considerable forgetting of previously indexed documents. We introduce a generative memory to sample pseudo-queries for documents and supplement them during continual indexing to prevent forgetting for the retrieval task.
  arXiv  Detail & Related papers  (2022-12-19T18:59:34Z)
• 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.