paper-with-me

홈 › Papers

ProFe: Communication-Efficient Decentralized Federated Learning via Distillation and Prototypes

2024-12-15 · Pedro Miguel Sánchez Sánchez, Enrique Tomás Martínez Beltrán, Miguel Fernández Llamas, Gérôme Bovet, Gregorio Martínez Pérez, Alberto Huertas Celdrán

Decentralized Federated Learning (DFL) trains models in a collaborative and privacy-preserving manner while removing model centralization risks and improving communication bottlenecks. However, DFL faces challenges in efficient communication management and model aggregation within decentralized environments, especially with heterogeneous data distributions. Thus, this paper introduces ProFe, a novel communication optimization algorithm for DFL that combines knowledge distillation, prototype learning, and quantization techniques. ProFe utilizes knowledge from large local models to train smaller ones for aggregation, incorporates prototypes to better learn unseen classes, and applies quantization to reduce data transmitted during communication rounds. The performance of ProFe has been validated and compared to the literature by using benchmark datasets like MNIST, CIFAR10, and CIFAR100. Results showed that the proposed algorithm reduces communication costs by up to ~40-50% while maintaining or improving model performance. In addition, it adds ~20% training time due to increased complexity, generating a trade-off.

📄 PDF Abstract BibTeX arXiv:2412.11207

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningKnowledge DistillationManagementPrivacy PreservingQuantization

Similar Papers 제목 키워드 기반

Towards efficient compression and communication for prototype-based decentralized learning

2024-11-14 · Pablo Fernández-Piñeiro, Manuel Ferández-Veiga, Rebeca P. Díaz-Redondo, Ana Fernández-Vilas 외

In prototype-based federated learning, the exchange of model parameters between clients and the master server is replaced by transmission of prototypes or quantized versions of the data samples to the aggregation server.…

Data CompressionFederated Learning

On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach

2025-08-05 · Jiahui Bai, Hai Dong, A. K. Qin arxiv

Decentralized Federated Learning (DFL) struggles with the slow adaptation of late-joining delayed clients and high communication costs in asynchronous environments. These limitations significantly hinder overall performa…

Federated Learning

Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments

2022-08-24 · Rui Song, Dai Liu, Dave Zhenyu Chen, Andreas Festag 외

In federated learning, all networked clients contribute to the model training cooperatively. However, with model sizes increasing, even sharing the trained partial models often leads to severe communication bottlenecks i…

Dataset DistillationFederated Learning

FedDKD: Federated Learning with Decentralized Knowledge Distillation

2022-05-02 · Xinjia Li, BoYu Chen, Wenlian Lu

The performance of federated learning in neural networks is generally influenced by the heterogeneity of the data distribution. For a well-performing global model, taking a weighted average of the local models, as done b…

Federated LearningKnowledge Distillation

FedKD: Communication Efficient Federated Learning via Knowledge Distillation

2021-08-30 · Chuhan Wu, Fangzhao Wu, Lingjuan Lyu, Yongfeng Huang 외

Federated learning is widely used to learn intelligent models from decentralized data. In federated learning, clients need to communicate their local model updates in each iteration of model learning. However, model upda…

Federated LearningKnowledge Distillation