Saved in:
Bibliographic Details
Main Authors: Lee, Minkwon, Kim, Hyoil, Joo, Changhee
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.15693
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912079358722048
author Lee, Minkwon
Kim, Hyoil
Joo, Changhee
author_facet Lee, Minkwon
Kim, Hyoil
Joo, Changhee
contents Federated learning (FL) is a decentralized AI mechanism suitable for a large number of devices like in smart IoT. A major challenge of FL is the non-IID dataset problem, originating from the heterogeneous data collected by FL participants, leading to performance deterioration of the trained global model. There have been various attempts to rectify non-IID dataset, mostly focusing on manipulating the collected data. This paper, however, proposes a novel approach to ensure data IIDness by properly clustering and grouping mobile IoT nodes exploiting their geographical characteristics, so that each FL group can achieve IID dataset. We first provide an experimental evidence for the independence and identicalness features of IoT data according to the inter-device distance, and then propose Dynamic Clustering and Partial-Steady Grouping algorithms that partition FL participants to achieve near-IIDness in their dataset while considering device mobility. Our mechanism significantly outperforms benchmark grouping algorithms at least by 110 times in terms of the joint cost between the number of dropout devices and the evenness in per-group device count, with a mild increase in the number of groups only by up to 0.93 groups.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15693
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Geographical Node Clustering and Grouping to Guarantee Data IIDness in Federated Learning
Lee, Minkwon
Kim, Hyoil
Joo, Changhee
Artificial Intelligence
Networking and Internet Architecture
Federated learning (FL) is a decentralized AI mechanism suitable for a large number of devices like in smart IoT. A major challenge of FL is the non-IID dataset problem, originating from the heterogeneous data collected by FL participants, leading to performance deterioration of the trained global model. There have been various attempts to rectify non-IID dataset, mostly focusing on manipulating the collected data. This paper, however, proposes a novel approach to ensure data IIDness by properly clustering and grouping mobile IoT nodes exploiting their geographical characteristics, so that each FL group can achieve IID dataset. We first provide an experimental evidence for the independence and identicalness features of IoT data according to the inter-device distance, and then propose Dynamic Clustering and Partial-Steady Grouping algorithms that partition FL participants to achieve near-IIDness in their dataset while considering device mobility. Our mechanism significantly outperforms benchmark grouping algorithms at least by 110 times in terms of the joint cost between the number of dropout devices and the evenness in per-group device count, with a mild increase in the number of groups only by up to 0.93 groups.
title Geographical Node Clustering and Grouping to Guarantee Data IIDness in Federated Learning
topic Artificial Intelligence
Networking and Internet Architecture
url https://arxiv.org/abs/2410.15693