RQ-GMM: Residual Quantized Gaussian Mixture Model for Multimodal Semantic Discretization in CTR Prediction

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Tong, Ziye, Liu, Jiahao, Zhang, Weimin, Ruan, Hongji, Tang, Derick, Zeng, Zhanpeng, Zeng, Qinsong, Zhang, Peng, Lu, Tun, Gu, Ning
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908832024756224
author Tong, Ziye
Liu, Jiahao
Zhang, Weimin
Ruan, Hongji
Tang, Derick
Zeng, Zhanpeng
Zeng, Qinsong
Zhang, Peng
Lu, Tun
Gu, Ning
author_facet Tong, Ziye
Liu, Jiahao
Zhang, Weimin
Ruan, Hongji
Tang, Derick
Zeng, Zhanpeng
Zeng, Qinsong
Zhang, Peng
Lu, Tun
Gu, Ning
contents Multimodal content is crucial for click-through rate (CTR) prediction. However, directly incorporating continuous embeddings from pre-trained models into CTR models yields suboptimal results due to misaligned optimization objectives and convergence speed inconsistency during joint training. Discretizing embeddings into semantic IDs before feeding them into CTR models offers a more effective solution, yet existing methods suffer from limited codebook utilization, reconstruction accuracy, and semantic discriminability. We propose RQ-GMM (Residual Quantized Gaussian Mixture Model), which introduces probabilistic modeling to better capture the statistical structure of multimodal embedding spaces. Through Gaussian Mixture Models combined with residual quantization, RQ-GMM achieves superior codebook utilization and reconstruction accuracy. Experiments on public datasets and online A/B tests on a large-scale short-video platform serving hundreds of millions of users demonstrate substantial improvements: RQ-GMM yields a 1.502% gain in Advertiser Value over strong baselines. The method has been fully deployed, serving daily recommendations for hundreds of millions of users.
format Preprint
id arxiv_https___arxiv_org_abs_2602_12593
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle RQ-GMM: Residual Quantized Gaussian Mixture Model for Multimodal Semantic Discretization in CTR Prediction
Tong, Ziye
Liu, Jiahao
Zhang, Weimin
Ruan, Hongji
Tang, Derick
Zeng, Zhanpeng
Zeng, Qinsong
Zhang, Peng
Lu, Tun
Gu, Ning
Information Retrieval
Artificial Intelligence
Multimodal content is crucial for click-through rate (CTR) prediction. However, directly incorporating continuous embeddings from pre-trained models into CTR models yields suboptimal results due to misaligned optimization objectives and convergence speed inconsistency during joint training. Discretizing embeddings into semantic IDs before feeding them into CTR models offers a more effective solution, yet existing methods suffer from limited codebook utilization, reconstruction accuracy, and semantic discriminability. We propose RQ-GMM (Residual Quantized Gaussian Mixture Model), which introduces probabilistic modeling to better capture the statistical structure of multimodal embedding spaces. Through Gaussian Mixture Models combined with residual quantization, RQ-GMM achieves superior codebook utilization and reconstruction accuracy. Experiments on public datasets and online A/B tests on a large-scale short-video platform serving hundreds of millions of users demonstrate substantial improvements: RQ-GMM yields a 1.502% gain in Advertiser Value over strong baselines. The method has been fully deployed, serving daily recommendations for hundreds of millions of users.
title RQ-GMM: Residual Quantized Gaussian Mixture Model for Multimodal Semantic Discretization in CTR Prediction
topic Information Retrieval
Artificial Intelligence
url https://arxiv.org/abs/2602.12593