CROSSAN: Towards Efficient and Effective Adaptation of Multiple Multimodal Foundation Models for Sequential Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fu, Junchen, Ni, Yongxin, Jose, Joemon M., Arapakis, Ioannis, Zheng, Kaiwen, Li, Youhua, Ge, Xuri
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909785094356992
author Fu, Junchen
Ni, Yongxin
Jose, Joemon M.
Arapakis, Ioannis
Zheng, Kaiwen
Li, Youhua
Ge, Xuri
author_facet Fu, Junchen
Ni, Yongxin
Jose, Joemon M.
Arapakis, Ioannis
Zheng, Kaiwen
Li, Youhua
Ge, Xuri
contents In this paper, we explore a less-studied yet practically important problem: how to efficiently and effectively adapt multiple ($>$2) multimodal foundation models (MFMs) for the sequential recommendation task. To this end, we propose a plug-and-play Cross-modal Side Adapter Network (CROSSAN), which leverages a fully decoupled side adapter-based paradigm to achieve efficient and scalable adaptation. Compared to the state-of-the-art efficient approaches, CROSSAN reduces training time by over 30%, GPU memory consumption by 20%, and trainable parameters by over 57%, while enabling effective cross-modal learning across diverse modalities. To further enhance multimodal fusion, we introduce the Mixture of Modality Expert Fusion (MOMEF) mechanism. Extensive experiments on public benchmarks demonstrate that CROSSAN consistently outperforms existing methods, achieving 6.7%--8.1% performance improvements when adapting four foundation models with raw modalities. Moreover, the overall performance continues to improve as more MFMs are incorporated. We will release our code and datasets to faciliate future research.
format Preprint
id arxiv_https___arxiv_org_abs_2504_10307
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CROSSAN: Towards Efficient and Effective Adaptation of Multiple Multimodal Foundation Models for Sequential Recommendation
Fu, Junchen
Ni, Yongxin
Jose, Joemon M.
Arapakis, Ioannis
Zheng, Kaiwen
Li, Youhua
Ge, Xuri
Information Retrieval
In this paper, we explore a less-studied yet practically important problem: how to efficiently and effectively adapt multiple ($>$2) multimodal foundation models (MFMs) for the sequential recommendation task. To this end, we propose a plug-and-play Cross-modal Side Adapter Network (CROSSAN), which leverages a fully decoupled side adapter-based paradigm to achieve efficient and scalable adaptation. Compared to the state-of-the-art efficient approaches, CROSSAN reduces training time by over 30%, GPU memory consumption by 20%, and trainable parameters by over 57%, while enabling effective cross-modal learning across diverse modalities. To further enhance multimodal fusion, we introduce the Mixture of Modality Expert Fusion (MOMEF) mechanism. Extensive experiments on public benchmarks demonstrate that CROSSAN consistently outperforms existing methods, achieving 6.7%--8.1% performance improvements when adapting four foundation models with raw modalities. Moreover, the overall performance continues to improve as more MFMs are incorporated. We will release our code and datasets to faciliate future research.
title CROSSAN: Towards Efficient and Effective Adaptation of Multiple Multimodal Foundation Models for Sequential Recommendation
topic Information Retrieval
url https://arxiv.org/abs/2504.10307