paper-with-me

홈 › Papers

Closing the Gap between Client and Global Model Performance in Heterogeneous Federated Learning

2022-11-07 · Hongrui Shi, Valentin Radu, Po Yang

The heterogeneity of hardware and data is a well-known and studied problem in the community of Federated Learning (FL) as running under heterogeneous settings. Recently, custom-size client models trained with Knowledge Distillation (KD) has emerged as a viable strategy for tackling the heterogeneity challenge. However, previous efforts in this direction are aimed at client model tuning rather than their impact onto the knowledge aggregation of the global model. Despite performance of global models being the primary objective of FL systems, under heterogeneous settings client models have received more attention. Here, we provide more insights into how the chosen approach for training custom client models has an impact on the global model, which is essential for any FL application. We show the global model can fully leverage the strength of KD with heterogeneous data. Driven by empirical observations, we further propose a new approach that combines KD and Learning without Forgetting (LwoF) to produce improved personalised models. We bring heterogeneous FL on pair with the mighty FedAvg of homogeneous FL, in realistic deployment scenarios with dropping clients.

📄 PDF Abstract BibTeX arXiv:2211.03457

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Adaptive Control of Client Selection and Gradient Compression for Efficient Federated Learning

2022-12-19 · Zhida Jiang, Yang Xu, Hongli Xu, Zhiyuan Wang 외

Federated learning (FL) allows multiple clients cooperatively train models without disclosing local data. However, the existing works fail to address all these practical concerns in FL: limited communication resources, d…

Federated Learning

Understanding and Improving Model Averaging in Federated Learning on Heterogeneous Data

2023-05-13 · Tailin Zhou, Zehong Lin, Jun Zhang, Danny H. K. Tsang

Model averaging is a widely adopted technique in federated learning (FL) that aggregates multiple client models to obtain a global model. Remarkably, model averaging in FL yields a superior global model, even when client…

Federated Learning

FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning

2024-03-25 · Xinyuan Ji, Zhaowei Zhu, Wei Xi, Olga Gadyatskaya 외

Federated Learning (FL) heavily depends on label quality for its performance. However, the label distribution among individual clients is always both noisy and heterogeneous. The high loss incurred by client-specific sam…

Federated Learning

FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction

2022-12-03 · Samiul Alam, Luyang Liu, Ming Yan, Mi Zhang

Most cross-device federated learning (FL) studies focus on the model-homogeneous setting where the global server model and local client models are identical. However, such constraint not only excludes low-end clients who…

Federated LearningmodelModel extraction

Leveraging Foundation Models to Improve Lightweight Clients in Federated Learning

2023-11-14 · Xidong Wu, Wan-Yi Lin, Devin Willmott, Filipe Condessa 외

Federated Learning (FL) is a distributed training paradigm that enables clients scattered across the world to cooperatively learn a global model without divulging confidential data. However, FL faces a significant challe…

Federated Learning