MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction

doi:10.1109/tkde.2026.3735698

MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction

2026-09-22

0

PRE

AI

DOI：10.1109/tkde.2026.3735698

Original

Original request for help

Save

Abstract

En 中文

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 MARS (Modality-Aligned Retrieval for Sequence 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 for low-active users on Kuaishou.

Keywords:

Click-Through rate

data augmentation

modality-aligned

MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction

Abstract

Journal

Organization

Cited Papers