paper-with-me

홈 › Papers

Federated Neural Architecture Search

2020-02-15 · Jinliang Yuan, Mengwei Xu, Yuxin Zhao, Kaigui Bian, Gang Huang, Xuanzhe Liu, Shangguang Wang

To preserve user privacy while enabling mobile intelligence, techniques have been proposed to train deep neural networks on decentralized data. However, training over decentralized data makes the design of neural architecture quite difficult as it already was. Such difficulty is further amplified when designing and deploying different neural architectures for heterogeneous mobile platforms. In this work, we propose an automatic neural architecture search into the decentralized training, as a new DNN training paradigm called Federated Neural Architecture Search, namely federated NAS. To deal with the primary challenge of limited on-client computational and communication resources, we present FedNAS, a highly optimized framework for efficient federated NAS. FedNAS fully exploits the key opportunity of insufficient model candidate re-training during the architecture search process, and incorporates three key optimizations: parallel candidates training on partial clients, early dropping candidates with inferior performance, and dynamic round numbers. Tested on large-scale datasets and typical CNN architectures, FedNAS achieves comparable model accuracy as state-of-the-art NAS algorithm that trains models with centralized data, and also reduces the client cost by up to two orders of magnitude compared to a straightforward design of federated NAS.

📄 PDF Abstract BibTeX arXiv:2002.06352

Code (0)

등록된 구현이 없습니다.

Tasks

Neural Architecture Search

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Real-time Federated Evolutionary Neural Architecture Search

2020-03-04 · Hangyu Zhu, Yaochu Jin

Federated learning is a distributed machine learning approach to privacy preservation and two major technical challenges prevent a wider application of federated learning. One is that federated learning raises high deman…

BIG-bench Machine LearningFederated LearningNeural Architecture Search

FedAutoMRI: Federated Neural Architecture Search for MR Image Reconstruction

2023-07-21 · Ruoyou Wu, Cheng Li, Juan Zou, Shanshan Wang

Centralized training methods have shown promising results in MR image reconstruction, but privacy concerns arise when gathering data from multiple institutions. Federated learning, a distributed collaborative training sc…

Federated LearningImage ReconstructionNeural Architecture Search

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

2020-04-18 · Chaoyang He, Murali Annavaram, Salman Avestimehr

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 …

Federated LearningNeural Architecture Search

SuperFedNAS: Cost-Efficient Federated Neural Architecture Search for On-Device Inference

2023-01-26 · Alind Khare, Animesh Agrawal, Aditya Annavajjala, Payman Behnam 외

Neural Architecture Search (NAS) for Federated Learning (FL) is an emerging field. It automates the design and training of Deep Neural Networks (DNNs) when data cannot be centralized due to privacy, communication costs, …

Federated LearningNeural Architecture SearchPrivacy Preserving

Self-supervised Cross-silo Federated Neural Architecture Search

2021-01-28 · Xinle Liang, Yang Liu, Jiahuan Luo, Yuanqin He 외

Federated Learning (FL) provides both model performance and data privacy for machine learning tasks where samples or features are distributed among different parties. In the training process of FL, no party has a global …

Federated LearningNeural Architecture SearchVertical Federated Learning