Revisiting scalable sequential recommendation with Multi-Embedding Approach and Mixture-of-Experts

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Qiushi, Wang, Hao, An, Guoyuan, Zhang, Luankang, Guo, Wei, Liu, Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914121872572416
author Pan, Qiushi
Wang, Hao
An, Guoyuan
Zhang, Luankang
Guo, Wei
Liu, Yong
author_facet Pan, Qiushi
Wang, Hao
An, Guoyuan
Zhang, Luankang
Guo, Wei
Liu, Yong
contents In recommendation systems, how to effectively scale up recommendation models has been an essential research topic. While significant progress has been made in developing advanced and scalable architectures for sequential recommendation(SR) models, there are still challenges due to items' multi-faceted characteristics and dynamic item relevance in the user context. To address these issues, we propose Fuxi-MME, a framework that integrates a multi-embedding strategy with a Mixture-of-Experts (MoE) architecture. Specifically, to efficiently capture diverse item characteristics in a decoupled manner, we decompose the conventional single embedding matrix into several lower-dimensional embedding matrices. Additionally, by substituting relevant parameters in the Fuxi Block with an MoE layer, our model achieves adaptive and specialized transformation of the enriched representations. Empirical results on public datasets show that our proposed framework outperforms several competitive baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25285
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Revisiting scalable sequential recommendation with Multi-Embedding Approach and Mixture-of-Experts
Pan, Qiushi
Wang, Hao
An, Guoyuan
Zhang, Luankang
Guo, Wei
Liu, Yong
Information Retrieval
In recommendation systems, how to effectively scale up recommendation models has been an essential research topic. While significant progress has been made in developing advanced and scalable architectures for sequential recommendation(SR) models, there are still challenges due to items' multi-faceted characteristics and dynamic item relevance in the user context. To address these issues, we propose Fuxi-MME, a framework that integrates a multi-embedding strategy with a Mixture-of-Experts (MoE) architecture. Specifically, to efficiently capture diverse item characteristics in a decoupled manner, we decompose the conventional single embedding matrix into several lower-dimensional embedding matrices. Additionally, by substituting relevant parameters in the Fuxi Block with an MoE layer, our model achieves adaptive and specialized transformation of the enriched representations. Empirical results on public datasets show that our proposed framework outperforms several competitive baselines.
title Revisiting scalable sequential recommendation with Multi-Embedding Approach and Mixture-of-Experts
topic Information Retrieval
url https://arxiv.org/abs/2510.25285