Pyramid Mixer: Multi-dimensional Multi-period Interest Modeling for Sequential Recommendation
Authors:
- Zhen GongZGZhen Gong
- Zhifang FanZFZhifang Fan
- Hui LuHLHui Lu
- Qiwei ChenQCQiwei Chen
- Chenbin ZhangCZChenbin Zhang
- Lin GuanLGLin Guan
- Yuchao ZhengYZYuchao Zheng
- Feng ZhangFZFeng Zhang
- Xiao YangXYXiao Yang
- Zuotao LiuZLZuotao Liu
Preprint
Abstract
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.Keywords
All Related Versions
- Version 1, 2025-06-20, ArXiv
- Published version: , 4380.
This publication has 2 references indexed in Scilit:
- ResMLP: Feedforward Networks for Image Classification With Data-Efficient TrainingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2022
- MLP4Rec: A Pure MLP Architecture for Sequential Recommendations2022