MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xiao, Yutian, Wang, Shukuan, Wang, Binhao, Zhang, Zhao, Zhang, Yanze, Liu, Shanqi, Feng, Chao, Li, Xiang, Zhuang, Fuzhen
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908512274087936
author Xiao, Yutian
Wang, Shukuan
Wang, Binhao
Zhang, Zhao
Zhang, Yanze
Liu, Shanqi
Feng, Chao
Li, Xiang
Zhuang, Fuzhen
author_facet Xiao, Yutian
Wang, Shukuan
Wang, Binhao
Zhang, Zhao
Zhang, Yanze
Liu, Shanqi
Feng, Chao
Li, Xiang
Zhuang, Fuzhen
contents Click-through rate (CTR) prediction serves as a cornerstone of recommender systems. Despite the strong performance of current CTR models based on user behavior modeling, they are still severely limited by interaction sparsity, especially in low-active user scenarios. To address this issue, data augmentation of user behavior is a promising research direction. However, existing data augmentation methods heavily rely on collaborative signals while overlooking the rich multimodal features of items, leading to insufficient modeling of low-active users. To alleviate this problem, we propose a novel framework \textbf{MARS} (\textbf{M}odality-\textbf{A}ligned \textbf{R}etrieval for \textbf{S}equence Augmented CTR Prediction). MARS utilizes a Stein kernel-based approach to align text and image features into a unified and unbiased semantic space to construct multimodal user embeddings. Subsequently, each low-active user's behavior sequence is augmented by retrieving, filtering, and concentrating the most similar behavior sequence of high-active users via multimodal user embeddings. Validated by extensive offline experiments and online A/B tests, our framework MARS consistently outperforms state-of-the-art baselines and achieves substantial growth on core business metrics within Kuaishou~\footnote{https://www.kuaishou.com/}. Consequently, MARS has been successfully deployed, serving the main traffic for hundreds of millions of users. To ensure reproducibility, we provide anonymous access to the implementation code~\footnote{https://github.com/wangshukuan/MARS}.
format Preprint
id arxiv_https___arxiv_org_abs_2509_01184
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction
Xiao, Yutian
Wang, Shukuan
Wang, Binhao
Zhang, Zhao
Zhang, Yanze
Liu, Shanqi
Feng, Chao
Li, Xiang
Zhuang, Fuzhen
Information Retrieval
Click-through rate (CTR) prediction serves as a cornerstone of recommender systems. Despite the strong performance of current CTR models based on user behavior modeling, they are still severely limited by interaction sparsity, especially in low-active user scenarios. To address this issue, data augmentation of user behavior is a promising research direction. However, existing data augmentation methods heavily rely on collaborative signals while overlooking the rich multimodal features of items, leading to insufficient modeling of low-active users. To alleviate this problem, we propose a novel framework \textbf{MARS} (\textbf{M}odality-\textbf{A}ligned \textbf{R}etrieval for \textbf{S}equence Augmented CTR Prediction). MARS utilizes a Stein kernel-based approach to align text and image features into a unified and unbiased semantic space to construct multimodal user embeddings. Subsequently, each low-active user's behavior sequence is augmented by retrieving, filtering, and concentrating the most similar behavior sequence of high-active users via multimodal user embeddings. Validated by extensive offline experiments and online A/B tests, our framework MARS consistently outperforms state-of-the-art baselines and achieves substantial growth on core business metrics within Kuaishou~\footnote{https://www.kuaishou.com/}. Consequently, MARS has been successfully deployed, serving the main traffic for hundreds of millions of users. To ensure reproducibility, we provide anonymous access to the implementation code~\footnote{https://github.com/wangshukuan/MARS}.
title MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction
topic Information Retrieval
url https://arxiv.org/abs/2509.01184