Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale

• URL: http://arxiv.org/abs/2603.00632v1
• Date: Sat, 28 Feb 2026 12:55:49 GMT
• Title: Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale
• Authors: Zheng Hu, Yuxin Chen, Yongsen Pan, Xu Yuan, Yuting Yin, Daoyuan Wang, Boyang Xia, Zefei Luo, Hongyang Wang, Songhao Ni, Dongxu Liang, Jun Wang, Shimin Cai, Tao Zhou, Fuji Ren, Wenwu Ou,
• Abstract summary: QuaSID is an end-to-end framework that learns collision-qualified SIDs by selectively qualified conflict pairs and scaling the repulsion strength by collision severity.<n> Experiments on public benchmarks and industrial data validate QuaSID.
• Score: 24.395492499196063
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semantic IDs (SIDs) are compact discrete representations derived from multimodal item features, serving as a unified abstraction for ID-based and generative recommendation. However, learning high-quality SIDs remains challenging due to two issues. (1) Collision problem: the quantized token space is prone to collisions, in which semantically distinct items are assigned identical or overly similar SID compositions, resulting in semantic entanglement. (2) Collision-signal heterogeneity: collisions are not uniformly harmful. Some reflect genuine conflicts between semantically unrelated items, while others stem from benign redundancy or systematic data effects. To address these challenges, we propose Qualification-Aware Semantic ID Learning (QuaSID), an end-to-end framework that learns collision-qualified SIDs by selectively repelling qualified conflict pairs and scaling the repulsion strength by collision severity. QuaSID consists of two mechanisms: Hamming-guided Margin Repulsion, which translates low-Hamming SID overlaps into explicit, severity-scaled geometric constraints on the encoder space; and Conflict-Aware Valid Pair Masking, which masks protocol-induced benign overlaps to denoise repulsion supervision. In addition, QuaSID incorporates a dual-tower contrastive objective to inject collaborative signals into tokenization. Experiments on public benchmarks and industrial data validate QuaSID. On public datasets, QuaSID consistently outperforms strong baselines, improving top-K ranking quality by 5.9% over the best baseline while increasing SID composition diversity. In an online A/B test on Kuaishou e-commerce with a 5% traffic split, QuaSID increases ranking GMV-S2 by 2.38% and improves completed orders on cold-start retrieval by up to 6.42%. Finally, we show that the proposed repulsion loss is plug-and-play and enhances a range of SID learning frameworks across datasets.

Related papers

• 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)
• R2LED: Equipping Retrieval and Refinement in Lifelong User Modeling with Semantic IDs for CTR Prediction [23.668401664583758]
  We propose a novel paradigm that equips retrieval and refinement in Lifelong User Modeling with SEmantic IDs (R2LED)<n>First, we introduce a Multi-route Mixed Retrieval for the retrieval stage. On the other hand, a mixed retrieval mechanism is proposed to efficiently retrieve candidates from both collaborative and semantic views.<n>For refinement, we design a Bi-level Fusion Refinement, including a target-aware cross-attention for route-level fusion and a gate mechanism for SID-level fusion.
  arXiv  Detail & Related papers  (2026-02-06T11:27:20Z)
• 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)
• MMQ-v2: Align, Denoise, and Amplify: Adaptive Behavior Mining for Semantic IDs Learning in Recommendation [19.071559026849208]
  We propose a mixture-of-quantization framework, MMQ-v2, to adaptively Align, Denoise, and Amplify multimodal information from content and behavior modalities for semantic IDs learning.<n>It introduces two innovations: an adaptive behavior-content alignment that is aware of information richness to shield representations from noise, and a dynamic behavioral router to amplify critical signals by applying different weights to SIDs.
  arXiv  Detail & Related papers  (2025-10-29T15:27:23Z)
• DiffGRM: Diffusion-based Generative Recommendation Model [63.35379395455103]
  Generative recommendation (GR) is an emerging paradigm that represents each item via a tokenizer as an n-digit semantic ID (SID)<n>We propose DiffGRM, a diffusion-based GR model that replaces the autoregressive decoder with a masked discrete diffusion model (MDM)<n> Experiments show consistent gains over strong generative and discriminative recommendation baselines on multiple datasets.
  arXiv  Detail & Related papers  (2025-10-21T03:23:32Z)
• Eigen-1: Adaptive Multi-Agent Refinement with Monitor-Based RAG for Scientific Reasoning [53.45095336430027]
  We develop a unified framework that combines implicit retrieval and structured collaboration.<n>On Humanity's Last Exam (HLE) Bio/Chem Gold, our framework achieves 48.3% accuracy.<n>Results on SuperGPQA and TRQA confirm robustness across domains.
  arXiv  Detail & Related papers  (2025-09-25T14:05:55Z)
• FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets [64.51403245281547]
  FORGE is a benchmark for FOrming semantic identifieR in Generative rEtrieval with industrial datasets.<n>For real-world applications, FORGE introduces an offline pretraining schema that reduces online convergence by half.
  arXiv  Detail & Related papers  (2025-09-25T08:44:22Z)
• Erasing, Transforming, and Noising Defense Network for Occluded Person Re-Identification [36.91680117072686]
  We propose Erasing, Transforming, and Noising Defense Network (ETNDNet) to solve occluded person re-ID. In the proposed ETNDNet, we randomly erase the feature map to create an adversarial representation with incomplete information. Thirdly, we perturb the feature map with random values to address noisy information introduced by obstacles and non-target pedestrians.
  arXiv  Detail & Related papers  (2023-07-14T06:42:21Z)
• Object Segmentation by Mining Cross-Modal Semantics [68.88086621181628]
  We propose a novel approach by mining the Cross-Modal Semantics to guide the fusion and decoding of multimodal features. Specifically, we propose a novel network, termed XMSNet, consisting of (1) all-round attentive fusion (AF), (2) coarse-to-fine decoder (CFD), and (3) cross-layer self-supervision.
  arXiv  Detail & Related papers  (2023-05-17T14:30:11Z)
• Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification [123.75412386783904]
  State-of-the-art object Re-ID approaches adopt clustering algorithms to generate pseudo-labels for the unlabeled target domain. We propose an uncertainty-aware clustering framework (UCF) for UDA tasks. Our UCF method consistently achieves state-of-the-art performance in multiple UDA tasks for object Re-ID.
  arXiv  Detail & Related papers  (2021-08-22T09:57:14Z)

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.