paper-with-me

홈 › Papers

FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning

2025-11-27 · Yuan Yao, Lixu Wang, Jiaqi Wu, Jin Song, Simin Chen, Zehua Wang, Zijian Tian, Wei Chen, Huixia Li, Xiaoxiao Li arxiv

Federated learning (FL) enables collaborative training across clients while preserving privacy. While most existing FL methods assume homogeneous model architectures, client heterogeneity in both data and resources makes this assumption impractical, thus motivating model-heterogeneous FL. To address this problem, we propose Federated Representation Entanglement (FedRE), a framework built upon a novel form of client knowledge termed entangled representation. Specifically, each client aggregates its local representations into a single entangled representation using normalized random weights, and then applies the same weights to integrate the corresponding one-hot label encodings into an entangled-label encoding. Both are subsequently uploaded to the server to train a global classifier. During training, each entangled representation is supervised across categories via its entangled-label encoding, while random weights are re-sampled at each round to introduce diversity, alleviating overconfidence in the global classifier and yielding smoother decision boundaries. Moreover, each client uploads a single entangled representation along with its entangled-label encoding, mitigating the risk of representation inversion attacks and reducing communication overhead. Extensive experiments demonstrate that FedRE achieves an effective trade-off among model performance, privacy protection, and communication overhead. The codes are available at https://github.com/AIResearch-Group/FedRE.

📄 PDF Abstract BibTeX arXiv:2511.22265

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

HeteFedRec: Federated Recommender Systems with Model Heterogeneity

2023-07-24 · Wei Yuan, Liang Qu, Lizhen Cui, Yongxin Tong 외

Owing to the nature of privacy protection, federated recommender systems (FedRecs) have garnered increasing interest in the realm of on-device recommender systems. However, most existing FedRecs only allow participating …

Knowledge DistillationmodelRecommendation Systems

Gradients as an Action: Towards Communication-Efficient Federated Recommender Systems via Adaptive Action Sharing

2025-07-08 · Zhufeng Lu, Chentao Jia, Ming Hu, Xiaofei Xie 외 arxiv

As a promising privacy-aware collaborative model training paradigm, Federated Learning (FL) is becoming popular in the design of distributed recommender systems. However, Federated Recommender Systems (FedRecs) greatly s…

Recommendation SystemsFederated LearningModel Compression

FedReFT: Federated Representation Fine-Tuning with All-But-Me Aggregation

2025-08-27 · Fatema Siddika, Md Anwar Hossen, J. Pablo Muñoz, Tanya Roosta 외 arxiv

Parameter-efficient fine-tuning (PEFT) adapts large pre-trained models by updating only a small subset of parameters. Recently, Representation Fine-Tuning (ReFT) has emerged as an effective alternative. ReFT shifts the f…

parameter-efficient fine-tuningArithmetic ReasoningFederated Learning

Personalized Recommendation Models in Federated Settings: A Survey

2025-03-10 · Chunxu Zhang, Guodong Long, Zijian Zhang, Zhiwei Li 외

Federated recommender systems (FedRecSys) have emerged as a pivotal solution for privacy-aware recommendations, balancing growing demands for data security and personalized experiences. Current research efforts predomina…

Recommendation SystemsSurvey

User Consented Federated Recommender System Against Personalized Attribute Inference Attack

2023-12-23 · Qi Hu, Yangqiu Song

Recommender systems can be privacy-sensitive. To protect users' private historical interactions, federated learning has been proposed in distributed learning for user representations. Using federated recommender (FedRec)…

AttributeFederated LearningInference AttackRecommendation Systems