Towards Non-I.I.D. and Invisible Data with FedNAS: Federated Deep Learning via Neural Architecture Search

2020/04/18 by Chaoyang He, He, Chaoyang, Murali Annavaram +3 · 30 citations
Computer Science · Mathematics · #Adversarial Robustness in Machine Learning #Archaeology #Architecture #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer architecture #Computer science #Cryptography and Data Security #Data science #Deep learning #Deep neural networks #Distributed #FOS: Computer and information sciences #History #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Multiagent Systems (cs.MA) #Parallel #Privacy-Preserving Technologies in Data #and Cluster Computing (cs.DC) #cs.CV #cs.DC #cs.LG #cs.MA #stat.ML

paper · pdf · doi:10.48550/arxiv.2004.08546

published in arXiv (Cornell University) (Cornell University) · accepted to CVPR 2020 workshop on neural architecture search and beyond for representation learning. Code is released at https://fedml.ai

openalex publication_date 2020/04/18 · openalex created_date 2020/11/09 · arxiv created 2021/01/04 · arxiv updated 2021/01/05 · openalex updated_date 2026/07/28

Abstract

Federated Learning (FL) has been proved to be an effective learning framework when data cannot be centralized due to privacy, communication costs, and regulatory restrictions. When training deep learning models under an FL setting, people employ the predefined model architecture discovered in the centralized environment. However, this predefined architecture may not be the optimal choice because it may not fit data with non-identical and independent distribution (non-IID). Thus, we advocate automating federated learning (AutoFL) to improve model accuracy and reduce the manual design effort. We specifically study AutoFL via Neural Architecture Search (NAS), which can automate the design process. We propose a Federated NAS (FedNAS) algorithm to help scattered workers collaboratively searching for a better architecture with higher accuracy. We also build a system based on FedNAS. Our experiments on non-IID dataset show that the architecture searched by FedNAS can outperform the manually predefined architecture.

Citations

• Towards Federated Learning at Scale: System Design
• Advances and Open Problems in Federated Learning
• FedML: A Research Library and Benchmark for Federated Machine Learning

Cited by

• Federated Whole Prostate Segmentation in MRI with Personalized Neural Architectures
• Self-supervised Cross-silo Federated Neural Architecture Search

Related

• Self-supervised Cross-silo Federated Neural Architecture Search
• Direct Federated Neural Architecture Search
• Federated Neural Architecture Search
• FDNAS: Improving Data Privacy and Model Diversity in AutoML
• From Federated Learning to Federated Neural Architecture Search: A Survey