DiffusionGS: Generative Search with Query Conditioned Diffusion in Kuaishou

TL;DR

DiffusionGS introduces a generative, diffusion-based model that aligns user queries with behavioral data to improve personalized search relevance in short-video platforms.

Contribution

The paper presents a novel query-conditioned diffusion approach and the User-aware Denoising Layer for better interest extraction from noisy historical behaviors.

Findings

Outperforms state-of-the-art methods in offline experiments

Achieves significant online engagement improvements

Effectively captures dynamic user interest shifts

Abstract

Personalized search ranking systems are critical for driving engagement and revenue in modern e-commerce and short-video platforms. While existing methods excel at estimating users' broad interests based on the filtered historical behaviors, they typically under-exploit explicit alignment between a user's real-time intent (represented by the user query) and their past actions. In this paper, we propose DiffusionGS, a novel and scalable approach powered by generative models. Our key insight is that user queries can serve as explicit intent anchors to facilitate the extraction of users' immediate interests from long-term, noisy historical behaviors. Specifically, we formulate interest extraction as a conditional denoising task, where the user's query guides a conditional diffusion process to produce a robust, user intent-aware representation from their behavioral sequence. We propose the User-aware Denoising Layer (UDL) to incorporate user-specific profiles into the optimization of attention distribution on the user's past actions. By reframing queries as intent priors and leveraging diffusion-based denoising, our method provides a powerful mechanism for capturing dynamic user interest shifts. Extensive offline and online experiments demonstrate the superiority of DiffusionGS over state-of-the-art methods.