A Survey of Personalized Federated Foundation Models for Privacy-Preserving Recommendation

2025/06/13 by Zhiwei Li, Li, Zhiwei, Guodong Long +9
Psychology · Social Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Gambling Behavior and Treatments #Machine Learning (cs.LG) #Names, Identity, and Discrimination Research #Personality Traits and Psychology

paper · pdf · doi:10.48550/arxiv.2506.11563

openalex publication_date 2025/06/13 · openalex created_date 2025/10/11 · openalex updated_date 2026/07/28

Abstract

Integrating Foundation Models (FMs) into recommendation systems is an emerging and promising research direction. However, centralized paradigms face growing pressure from privacy concerns and strict regulatory requirements. Federated learning offers a viable solution that enables collaborative model refinement while keeping raw user data on local devices or organizational silos. Yet, applying FMs in this setting creates a fundamental tension, where the system must balance the leverage of global knowledge with the necessity of capturing user personality. This survey provides a comprehensive overview of Personalized Federated Foundation Models for privacy-preserving recommendation, and reviews recent progress in this emerging field. We first analyze personalization techniques that function effectively under federated settings. Furthermore, we discuss the adaptation of foundation models to such federated architectures to balance generalization with user-specific needs for achieving privacy-preserving recommendation. In contrast to existing reviews, our work specifically emphasizes the architectural intersection of federation, personalization, and foundation models. \looseness=-1

Citations

• Privacy Risks of LLM-Empowered Recommender Systems: An Inversion Attack Perspective
• FedSC: Federated Learning with Semantic-Aware Collaboration
• Prompt Inference Attack on Distributed Large Language Model Inference Frameworks
• Personalized Recommendation Models in Federated Settings: A Survey
• Multifaceted User Modeling in Recommendation: A Federated Foundation Models Approach
• Mixture of Experts Made Personalized: Federated Prompt Learning for Vision-Language Models
• Federated Vision-Language-Recommendation with Personalized Fusion
• FedSlate:A Federated Deep Reinforcement Learning Recommender System
• Federated Adaptation for Foundation Model-based Recommendations
• Advances and Open Challenges in Federated Foundation Models
• Dual-Personalizing Adapter for Federated Foundation Models
• Analysis of Privacy Leakage in Federated Large Language Models
• When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method
• Grounding Foundation Models through Federated Transfer Learning: A General Framework
• Latent Space Translation via Semantic Alignment
• A Survey on Large Language Models for Recommendation
• When Federated Recommendation Meets Cold-Start Problem: Separating Item Attributes and User Interactions
• Federated Foundation Models: Privacy-Preserving and Collaborative Learning for Large Models
• Visual Prompt Based Personalized Federated Learning
• A Survey on User Behavior Modeling in Recommender Systems
• A Comprehensive Survey on Pretrained Foundation Models: A History from BERT to ChatGPT
• Pre-train, Prompt and Recommendation: A Comprehensive Survey of Language Modelling Paradigm Adaptations in Recommender Systems
• Federated Recommendation with Additive Personalization
• Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning
• Exploring Parameter-Efficient Fine-Tuning to Enable Foundation Models in Federated Learning
• Trading Off Privacy, Utility and Efficiency in Federated Learning
• Comprehensive Privacy Analysis on Federated Recommender System against Attribute Inference Attacks
• FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks
• Deep Leakage from Gradients
• Exploiting Unintended Feature Leakage in Collaborative Learning
• TransFR: Transferable Federated Recommendation with Adapter Tuning on Pre-trained Language Models

Related

• Federated Adaptation for Foundation Model-based Recommendations
• Multifaceted User Modeling in Recommendation: A Federated Foundation Models Approach
• A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms
• A Tutorial of Personalized Federated Recommender Systems: Recent Advances and Future Directions
• Foundation Models for Recommender Systems: A Survey and New Perspectives