Saved in:
Bibliographic Details
Main Authors: Feng, Haozhe, Pang, Tianyu, Du, Chao, Chen, Wei, Yan, Shuicheng, Lin, Min
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2301.12195
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916330568941568
author Feng, Haozhe
Pang, Tianyu
Du, Chao
Chen, Wei
Yan, Shuicheng
Lin, Min
author_facet Feng, Haozhe
Pang, Tianyu
Du, Chao
Chen, Wei
Yan, Shuicheng
Lin, Min
contents Federated learning (FL) is a general principle for decentralized clients to train a server model collectively without sharing local data. FL is a promising framework with practical applications, but its standard training paradigm requires the clients to backpropagate through the model to compute gradients. Since these clients are typically edge devices and not fully trusted, executing backpropagation on them incurs computational and storage overhead as well as white-box vulnerability. In light of this, we develop backpropagation-free federated learning, dubbed BAFFLE, in which backpropagation is replaced by multiple forward processes to estimate gradients. BAFFLE is 1) memory-efficient and easily fits uploading bandwidth; 2) compatible with inference-only hardware optimization and model quantization or pruning; and 3) well-suited to trusted execution environments, because the clients in BAFFLE only execute forward propagation and return a set of scalars to the server. Empirically we use BAFFLE to train deep models from scratch or to finetune pretrained models, achieving acceptable results. Code is available in https://github.com/FengHZ/BAFFLE.
format Preprint
id arxiv_https___arxiv_org_abs_2301_12195
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle BAFFLE: A Baseline of Backpropagation-Free Federated Learning
Feng, Haozhe
Pang, Tianyu
Du, Chao
Chen, Wei
Yan, Shuicheng
Lin, Min
Machine Learning
Artificial Intelligence
Cryptography and Security
Distributed, Parallel, and Cluster Computing
Federated learning (FL) is a general principle for decentralized clients to train a server model collectively without sharing local data. FL is a promising framework with practical applications, but its standard training paradigm requires the clients to backpropagate through the model to compute gradients. Since these clients are typically edge devices and not fully trusted, executing backpropagation on them incurs computational and storage overhead as well as white-box vulnerability. In light of this, we develop backpropagation-free federated learning, dubbed BAFFLE, in which backpropagation is replaced by multiple forward processes to estimate gradients. BAFFLE is 1) memory-efficient and easily fits uploading bandwidth; 2) compatible with inference-only hardware optimization and model quantization or pruning; and 3) well-suited to trusted execution environments, because the clients in BAFFLE only execute forward propagation and return a set of scalars to the server. Empirically we use BAFFLE to train deep models from scratch or to finetune pretrained models, achieving acceptable results. Code is available in https://github.com/FengHZ/BAFFLE.
title BAFFLE: A Baseline of Backpropagation-Free Federated Learning
topic Machine Learning
Artificial Intelligence
Cryptography and Security
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2301.12195