MMQ-v2: Align, Denoise, and Amplify: Adaptive Behavior Mining for Semantic IDs Learning in Recommendation

• URL: http://arxiv.org/abs/2510.25622v2
• Date: Thu, 30 Oct 2025 02:50:46 GMT
• Title: MMQ-v2: Align, Denoise, and Amplify: Adaptive Behavior Mining for Semantic IDs Learning in Recommendation
• Authors: Yi Xu, Moyu Zhang, Chaofan Fan, Jinxin Hu, Xiaochen Li, Yu Zhang, Xiaoyi Zeng, Jing Zhang,
• Abstract summary: 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.
• Score: 19.071559026849208
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Industrial recommender systems rely on unique Item Identifiers (ItemIDs). However, this method struggles with scalability and generalization in large, dynamic datasets that have sparse long-tail data. Content-based Semantic IDs (SIDs) address this by sharing knowledge through content quantization. However, by ignoring dynamic behavioral properties, purely content-based SIDs have limited expressive power. Existing methods attempt to incorporate behavioral information but overlook a critical distinction: unlike relatively uniform content features, user-item interactions are highly skewed and diverse, creating a vast information gap in quality and quantity between popular and long-tail items. This oversight leads to two critical limitations: (1) Noise Corruption: Indiscriminate behavior-content alignment allows collaborative noise from long-tail items to corrupt their content representations, leading to the loss of critical multimodal information. (2)Signal Obscurity: The equal-weighting scheme for SIDs fails to reflect the varying importance of different behavioral signals, making it difficult for downstream tasks to distinguish important SIDs from uninformative ones. To tackle these issues, 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. The semantic IDs generated by this framework named ADA-SID. 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. Extensive experiments on public and large-scale industrial datasets demonstrate ADA-SID's significant superiority in both generative and discriminative recommendation tasks.

Related papers

• Stop Treating Collisions Equally: Qualification-Aware Semantic ID Learning for Recommendation at Industrial Scale [24.395492499196063]
  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.
  arXiv  Detail & Related papers  (2026-02-28T12:55:49Z)
• Test-time Adaptive Hierarchical Co-enhanced Denoising Network for Reliable Multimodal Classification [55.56234913868664]
  We propose Test-time Adaptive Hierarchical Co-enhanced Denoising Network (TAHCD) for reliable learning on multimodal data.<n>The proposed method achieves superior classification performance, robustness, and generalization compared with state-of-the-art reliable multimodal learning approaches.
  arXiv  Detail & Related papers  (2026-01-12T03:14:12Z)
• 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: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation [16.81485354427923]
  We propose Multimodal Mixture-of-Quantization (MMQ), a two-stage framework that trains a novel multimodal tokenizer.<n> MMQ unifies multimodal synergy, specificity, and behavioral adaptation, providing a scalable and versatile solution for both generative retrieval and discriminative ranking tasks.
  arXiv  Detail & Related papers  (2025-08-21T06:15:49Z)
• DAS: Dual-Aligned Semantic IDs Empowered Industrial Recommender System [15.648601380538413]
  We propose a one-stage Dual-Aligned Semantic IDs (DAS) method that simultaneously optimize quantization and alignment.<n>DAS achieves more efficient alignment between the semantic IDs and collaborative signals, with the following two innovative approaches.<n>DAS is successfully deployed across various advertising scenarios at Kuaishou App, serving over 400 million users daily.
  arXiv  Detail & Related papers  (2025-08-14T12:22:51Z)
• PartFormer: Awakening Latent Diverse Representation from Vision Transformer for Object Re-Identification [73.64560354556498]
  Vision Transformer (ViT) tends to overfit on most distinct regions of training data, limiting its generalizability and attention to holistic object features. We present PartFormer, an innovative adaptation of ViT designed to overcome the limitations in object Re-ID tasks. Our framework significantly outperforms state-of-the-art by 2.4% mAP scores on the most challenging MSMT17 dataset.
  arXiv  Detail & Related papers  (2024-08-29T16:31:05Z)
• 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)
• Dual Semantic Knowledge Composed Multimodal Dialog Systems [114.52730430047589]
  We propose a novel multimodal task-oriented dialog system named MDS-S2. It acquires the context related attribute and relation knowledge from the knowledge base. We also devise a set of latent query variables to distill the semantic information from the composed response representation.
  arXiv  Detail & Related papers  (2023-05-17T06:33:26Z)
• Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification [208.1227090864602]
  Visible-infrared person re-identification (VI-ReID) is a challenging cross-modality pedestrian retrieval problem. Existing VI-ReID methods tend to learn global representations, which have limited discriminability and weak robustness to noisy images. We propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID.
  arXiv  Detail & Related papers  (2020-07-18T03:08:13Z)
• An Attention-Based Deep Learning Model for Multiple Pedestrian Attributes Recognition [4.6898263272139795]
  This paper provides a novel solution to the problem of automatic characterization of pedestrians in surveillance footage. We propose a multi-task deep model that uses an element-wise multiplication layer to extract more comprehensive feature representations. Our experiments were performed on two well-known datasets (RAP and PETA) and point for the superiority of the proposed method with respect to the state-of-the-art.
  arXiv  Detail & Related papers  (2020-04-02T16:21:14Z)

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.