Enhancing Efficiency in Multidevice Federated Learning through Data Selection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mo, Fan, Malekzadeh, Mohammad, Chatterjee, Soumyajit, Kawsar, Fahim, Mathur, Akhil
Format: Preprint
Published: 2022
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917063027589120
author Mo, Fan
Malekzadeh, Mohammad
Chatterjee, Soumyajit
Kawsar, Fahim
Mathur, Akhil
author_facet Mo, Fan
Malekzadeh, Mohammad
Chatterjee, Soumyajit
Kawsar, Fahim
Mathur, Akhil
contents Ubiquitous wearable and mobile devices provide access to a diverse set of data. However, the mobility demand for our devices naturally imposes constraints on their computational and communication capabilities. A solution is to locally learn knowledge from data captured by ubiquitous devices, rather than to store and transmit the data in its original form. In this paper, we develop a federated learning framework, called Centaur, to incorporate on-device data selection at the edge, which allows partition-based training of a deep neural nets through collaboration between constrained and resourceful devices within the multidevice ecosystem of the same user. We benchmark on five neural net architecture and six datasets that include image data and wearable sensor time series. On average, Centaur achieves ~19% higher classification accuracy and ~58% lower federated training latency, compared to the baseline. We also evaluate Centaur when dealing with imbalanced non-iid data, client participation heterogeneity, and different mobility patterns. To encourage further research in this area, we release our code at https://github.com/nokia-bell-labs/data-centric-federated-learning
format Preprint
id arxiv_https___arxiv_org_abs_2211_04175
institution arXiv
publishDate 2022
record_format arxiv
spellingShingle Enhancing Efficiency in Multidevice Federated Learning through Data Selection
Mo, Fan
Malekzadeh, Mohammad
Chatterjee, Soumyajit
Kawsar, Fahim
Mathur, Akhil
Machine Learning
Ubiquitous wearable and mobile devices provide access to a diverse set of data. However, the mobility demand for our devices naturally imposes constraints on their computational and communication capabilities. A solution is to locally learn knowledge from data captured by ubiquitous devices, rather than to store and transmit the data in its original form. In this paper, we develop a federated learning framework, called Centaur, to incorporate on-device data selection at the edge, which allows partition-based training of a deep neural nets through collaboration between constrained and resourceful devices within the multidevice ecosystem of the same user. We benchmark on five neural net architecture and six datasets that include image data and wearable sensor time series. On average, Centaur achieves ~19% higher classification accuracy and ~58% lower federated training latency, compared to the baseline. We also evaluate Centaur when dealing with imbalanced non-iid data, client participation heterogeneity, and different mobility patterns. To encourage further research in this area, we release our code at https://github.com/nokia-bell-labs/data-centric-federated-learning
title Enhancing Efficiency in Multidevice Federated Learning through Data Selection
topic Machine Learning
url https://arxiv.org/abs/2211.04175