Generative Representational Learning of Foundation Models for Recommendation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Zheli, Zhu, Chenxu, Lin, Jianghao, Chen, Bo, Tang, Ruiming, Zhang, Weinan, Yu, Yong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913919782617088
author Zhou, Zheli
Zhu, Chenxu
Lin, Jianghao
Chen, Bo
Tang, Ruiming
Zhang, Weinan
Yu, Yong
author_facet Zhou, Zheli
Zhu, Chenxu
Lin, Jianghao
Chen, Bo
Tang, Ruiming
Zhang, Weinan
Yu, Yong
contents Developing a single foundation model with the capability to excel across diverse tasks has been a long-standing objective in the field of artificial intelligence. As the wave of general-purpose foundation models sweeps across various domains, their influence has significantly extended to the field of recommendation systems. While recent efforts have explored recommendation foundation models for various generative tasks, they often overlook crucial embedding tasks and struggle with the complexities of multi-task learning, including knowledge sharing & conflict resolution, and convergence speed inconsistencies. To address these limitations, we introduce RecFound, a generative representational learning framework for recommendation foundation models. We construct the first comprehensive dataset for recommendation foundation models covering both generative and embedding tasks across diverse scenarios. Based on this dataset, we propose a novel multi-task training scheme featuring a Task-wise Mixture of Low-rank Experts (TMoLE) to handle knowledge sharing & conflict, a Step-wise Convergence-oriented Sample Scheduler (S2Sched) to address inconsistent convergence, and a Model Merge module to balance the performance across tasks. Experiments demonstrate that RecFound achieves state-of-the-art performance across various recommendation tasks, outperforming existing baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11999
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Representational Learning of Foundation Models for Recommendation
Zhou, Zheli
Zhu, Chenxu
Lin, Jianghao
Chen, Bo
Tang, Ruiming
Zhang, Weinan
Yu, Yong
Information Retrieval
Computation and Language
Developing a single foundation model with the capability to excel across diverse tasks has been a long-standing objective in the field of artificial intelligence. As the wave of general-purpose foundation models sweeps across various domains, their influence has significantly extended to the field of recommendation systems. While recent efforts have explored recommendation foundation models for various generative tasks, they often overlook crucial embedding tasks and struggle with the complexities of multi-task learning, including knowledge sharing & conflict resolution, and convergence speed inconsistencies. To address these limitations, we introduce RecFound, a generative representational learning framework for recommendation foundation models. We construct the first comprehensive dataset for recommendation foundation models covering both generative and embedding tasks across diverse scenarios. Based on this dataset, we propose a novel multi-task training scheme featuring a Task-wise Mixture of Low-rank Experts (TMoLE) to handle knowledge sharing & conflict, a Step-wise Convergence-oriented Sample Scheduler (S2Sched) to address inconsistent convergence, and a Model Merge module to balance the performance across tasks. Experiments demonstrate that RecFound achieves state-of-the-art performance across various recommendation tasks, outperforming existing baselines.
title Generative Representational Learning of Foundation Models for Recommendation
topic Information Retrieval
Computation and Language
url https://arxiv.org/abs/2506.11999