Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gong, Zhen, Fan, Zhifang, Lu, Hui, Chen, Qiwei, Zhang, Chenbin, Guan, Lin, Zheng, Yuchao, Zhang, Feng, Yang, Xiao, Liu, Zuotao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918066140479488
author Gong, Zhen
Fan, Zhifang
Lu, Hui
Chen, Qiwei
Zhang, Chenbin
Guan, Lin
Zheng, Yuchao
Zhang, Feng
Yang, Xiao
Liu, Zuotao
author_facet Gong, Zhen
Fan, Zhifang
Lu, Hui
Chen, Qiwei
Zhang, Chenbin
Guan, Lin
Zheng, Yuchao
Zhang, Feng
Yang, Xiao
Liu, Zuotao
contents Sequential recommendation, a critical task in recommendation systems, predicts the next user action based on the understanding of the user's historical behaviors. Conventional studies mainly focus on cross-behavior modeling with self-attention based methods while neglecting comprehensive user interest modeling for more dimensions. In this study, we propose a novel sequential recommendation model, Pyramid Mixer, which leverages the MLP-Mixer architecture to achieve efficient and complete modeling of user interests. Our method learns comprehensive user interests via cross-behavior and cross-feature user sequence modeling. The mixer layers are stacked in a pyramid way for cross-period user temporal interest learning. Through extensive offline and online experiments, we demonstrate the effectiveness and efficiency of our method, and we obtain a +0.106% improvement in user stay duration and a +0.0113% increase in user active days in the online A/B test. The Pyramid Mixer has been successfully deployed on the industrial platform, demonstrating its scalability and impact in real-world applications.
format Preprint
id arxiv_https___arxiv_org_abs_2506_16942
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation
Gong, Zhen
Fan, Zhifang
Lu, Hui
Chen, Qiwei
Zhang, Chenbin
Guan, Lin
Zheng, Yuchao
Zhang, Feng
Yang, Xiao
Liu, Zuotao
Information Retrieval
Sequential recommendation, a critical task in recommendation systems, predicts the next user action based on the understanding of the user's historical behaviors. Conventional studies mainly focus on cross-behavior modeling with self-attention based methods while neglecting comprehensive user interest modeling for more dimensions. In this study, we propose a novel sequential recommendation model, Pyramid Mixer, which leverages the MLP-Mixer architecture to achieve efficient and complete modeling of user interests. Our method learns comprehensive user interests via cross-behavior and cross-feature user sequence modeling. The mixer layers are stacked in a pyramid way for cross-period user temporal interest learning. Through extensive offline and online experiments, we demonstrate the effectiveness and efficiency of our method, and we obtain a +0.106% improvement in user stay duration and a +0.0113% increase in user active days in the online A/B test. The Pyramid Mixer has been successfully deployed on the industrial platform, demonstrating its scalability and impact in real-world applications.
title Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2506.16942