KuaiFormer: Transformer-Based Retrieval at Kuaishou

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Chi, Cao, Jiangxia, Huang, Rui, Zheng, Kai, Luo, Qiang, Gai, Kun, Zhou, Guorui
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909391188393984
author Liu, Chi
Cao, Jiangxia
Huang, Rui
Zheng, Kai
Luo, Qiang
Gai, Kun
Zhou, Guorui
author_facet Liu, Chi
Cao, Jiangxia
Huang, Rui
Zheng, Kai
Luo, Qiang
Gai, Kun
Zhou, Guorui
contents In large-scale content recommendation systems, retrieval serves as the initial stage in the pipeline, responsible for selecting thousands of candidate items from billions of options to pass on to ranking modules. Traditionally, the dominant retrieval method has been Embedding-Based Retrieval (EBR) using a Deep Neural Network (DNN) dual-tower structure. However, applying transformer in retrieval tasks has been the focus of recent research, though real-world industrial deployment still presents significant challenges. In this paper, we introduce KuaiFormer, a novel transformer-based retrieval framework deployed in a large-scale content recommendation system. KuaiFormer fundamentally redefines the retrieval process by shifting from conventional score estimation tasks (such as click-through rate estimate) to a transformer-driven Next Action Prediction paradigm. This shift enables more effective real-time interest acquisition and multi-interest extraction, significantly enhancing retrieval performance. KuaiFormer has been successfully integrated into Kuaishou App's short-video recommendation system since May 2024, serving over 400 million daily active users and resulting in a marked increase in average daily usage time of Kuaishou users. We provide insights into both the technical and business aspects of deploying transformer in large-scale recommendation systems, addressing practical challenges encountered during industrial implementation. Our findings offer valuable guidance for engineers and researchers aiming to leverage transformer models to optimize large-scale content recommendation systems.
format Preprint
id arxiv_https___arxiv_org_abs_2411_10057
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle KuaiFormer: Transformer-Based Retrieval at Kuaishou
Liu, Chi
Cao, Jiangxia
Huang, Rui
Zheng, Kai
Luo, Qiang
Gai, Kun
Zhou, Guorui
Information Retrieval
Artificial Intelligence
Machine Learning
In large-scale content recommendation systems, retrieval serves as the initial stage in the pipeline, responsible for selecting thousands of candidate items from billions of options to pass on to ranking modules. Traditionally, the dominant retrieval method has been Embedding-Based Retrieval (EBR) using a Deep Neural Network (DNN) dual-tower structure. However, applying transformer in retrieval tasks has been the focus of recent research, though real-world industrial deployment still presents significant challenges. In this paper, we introduce KuaiFormer, a novel transformer-based retrieval framework deployed in a large-scale content recommendation system. KuaiFormer fundamentally redefines the retrieval process by shifting from conventional score estimation tasks (such as click-through rate estimate) to a transformer-driven Next Action Prediction paradigm. This shift enables more effective real-time interest acquisition and multi-interest extraction, significantly enhancing retrieval performance. KuaiFormer has been successfully integrated into Kuaishou App's short-video recommendation system since May 2024, serving over 400 million daily active users and resulting in a marked increase in average daily usage time of Kuaishou users. We provide insights into both the technical and business aspects of deploying transformer in large-scale recommendation systems, addressing practical challenges encountered during industrial implementation. Our findings offer valuable guidance for engineers and researchers aiming to leverage transformer models to optimize large-scale content recommendation systems.
title KuaiFormer: Transformer-Based Retrieval at Kuaishou
topic Information Retrieval
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2411.10057