paper-with-me

홈 › Papers

FedDrop: Trajectory-weighted Dropout for Efficient Federated Learning

2021-09-29 · Dongping Liao, Xitong Gao, Yiren Zhao, Hao Dai, Li Li, Kafeng Wang, Kejiang Ye, Yang Wang, Cheng-Zhong Xu

Federated learning (FL) enables edge clients to train collaboratively while preserving individual's data privacy. As clients do not inherently share identical data distributions, they may disagree in the direction of parameter updates, resulting in high compute and communication costs in comparison to centralized learning. Recent advances in FL focus on reducing data transmission during training; yet they neglected the increase of computational cost that dwarfs the merit of reduced communication. To this end, we propose FedDrop, which introduces channel-wise weighted dropout layers between convolutions to accelerate training while minimizing their impact on convergence. Empirical results show that FedDrop can drastically reduce the amount of FLOPs required for training with a small increase in communication, and push the Pareto frontier of communication/computation trade-off further than competing FL algorithms.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

FedDropoutAvg: Generalizable federated learning for histopathology image classification

2021-11-25 · Gozde N. Gunesli, Mohsin Bilal, Shan E Ahmed Raza, Nasir M. Rajpoot

Federated learning (FL) enables collaborative learning of a deep learning model without sharing the data of participating sites. FL in medical image analysis tasks is relatively new and open for enhancements. In this stu…

ClassificationFederated Learningimage-classificationImage Classification+1

Federated Dropout -- A Simple Approach for Enabling Federated Learning on Resource Constrained Devices

2021-09-30 · Dingzhu Wen, Ki-Jun Jeon, Kaibin Huang

Federated learning (FL) is a popular framework for training an AI model using distributed mobile data in a wireless network. It features data parallelism by distributing the learning task to multiple edge devices while a…

Federated Learning

Straggler-resilient Federated Learning: Tackling Computation Heterogeneity with Layer-wise Partial Model Training in Mobile Edge Network

2023-11-16 · Hongda Wu, Ping Wang, C V Aswartha Narayana

Federated Learning (FL) enables many resource-limited devices to train a model collaboratively without data sharing. However, many existing works focus on model-homogeneous FL, where the global and local models are the s…

Federated Learning

Enabling On-Device Training of Speech Recognition Models with Federated Dropout

2021-10-07 · Dhruv Guliani, Lillian Zhou, Changwan Ryu, Tien-Ju Yang 외

Federated learning can be used to train machine learning models on the edge on local data that never leave devices, providing privacy by default. This presents a challenge pertaining to the communication and computation …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Federated Learningspeech-recognition+1

Federated Dropout: Convergence Analysis and Resource Allocation

2024-12-31 · Sijing Xie, Dingzhu Wen, Xiaonan Liu, Changsheng You 외

Federated Dropout is an efficient technique to overcome both communication and computation bottlenecks for deploying federated learning at the network edge. In each training round, an edge device only needs to update and…

Federated Learning