Self-supervised Cross-silo Federated Neural Architecture Search

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liang, Xinle, Liu, Yang, Luo, Jiahuan, He, Yuanqin, Chen, Tianjian, Yang, Qiang
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909365239283712
author Liang, Xinle
Liu, Yang
Luo, Jiahuan
He, Yuanqin
Chen, Tianjian
Yang, Qiang
author_facet Liang, Xinle
Liu, Yang
Luo, Jiahuan
He, Yuanqin
Chen, Tianjian
Yang, Qiang
contents 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 view of data distributions or model architectures of other parties. Thus the manually-designed architectures may not be optimal. In the past, Neural Architecture Search (NAS) has been applied to FL to address this critical issue. However, existing Federated NAS approaches require prohibitive communication and computation effort, as well as the availability of high-quality labels. In this work, we present Self-supervised Vertical Federated Neural Architecture Search (SS-VFNAS) for automating FL where participants hold feature-partitioned data, a common cross-silo scenario called Vertical Federated Learning (VFL). In the proposed framework, each party first conducts NAS using self-supervised approach to find a local optimal architecture with its own data. Then, parties collaboratively improve the local optimal architecture in a VFL framework with supervision. We demonstrate experimentally that our approach has superior performance, communication efficiency and privacy compared to Federated NAS and is capable of generating high-performance and highly-transferable heterogeneous architectures even with insufficient overlapping samples, providing automation for those parties without deep learning expertise.
format Preprint
id arxiv_https___arxiv_org_abs_2101_11896
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Self-supervised Cross-silo Federated Neural Architecture Search
Liang, Xinle
Liu, Yang
Luo, Jiahuan
He, Yuanqin
Chen, Tianjian
Yang, Qiang
Machine Learning
Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
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 view of data distributions or model architectures of other parties. Thus the manually-designed architectures may not be optimal. In the past, Neural Architecture Search (NAS) has been applied to FL to address this critical issue. However, existing Federated NAS approaches require prohibitive communication and computation effort, as well as the availability of high-quality labels. In this work, we present Self-supervised Vertical Federated Neural Architecture Search (SS-VFNAS) for automating FL where participants hold feature-partitioned data, a common cross-silo scenario called Vertical Federated Learning (VFL). In the proposed framework, each party first conducts NAS using self-supervised approach to find a local optimal architecture with its own data. Then, parties collaboratively improve the local optimal architecture in a VFL framework with supervision. We demonstrate experimentally that our approach has superior performance, communication efficiency and privacy compared to Federated NAS and is capable of generating high-performance and highly-transferable heterogeneous architectures even with insufficient overlapping samples, providing automation for those parties without deep learning expertise.
title Self-supervised Cross-silo Federated Neural Architecture Search
topic Machine Learning
Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2101.11896