Full Text:
<111>
CLC number:
On-line Access: 2025-04-11
Received: 2024-09-13
Revision Accepted: 2025-01-08
Crosschecked: 0000-00-00
Cited: 0
Clicked: 148
Federated model with contrastive learning and adaptive control variates for Human activity recognition
| |||||||||||||
Ignatius IWAN, Bernardo nugroho YAHYA‡, Seoklyong LEE. Federated model with contrastive learning and adaptive control variates for Human activity recognition[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .
@article{title="Federated model with contrastive learning and adaptive control variates for Human activity recognition",
author="Ignatius IWAN, Bernardo nugroho YAHYA‡, Seoklyong LEE",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2400797"
}
%0 Journal Article
%T Federated model with contrastive learning and adaptive control variates for Human activity recognition
%A Ignatius IWAN
%A Bernardo nugroho YAHYA‡
%A Seoklyong LEE
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2400797
TY - JOUR
T1 - Federated model with contrastive learning and adaptive control variates for Human activity recognition
A1 - Ignatius IWAN
A1 - Bernardo nugroho YAHYA‡
A1 - Seoklyong LEE
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2400797
Abstract: The recent attention to privacy issues demands a communication-safe method for training human activity recognition (HAR) models on client activity data. federated learning (FL) has become a compelling technique to facilitate model training between the server and clients while preserving data privacy. However, classical FL methods often assume Independent and Identically Distributed (IID) data among clients. This assumption does not hold true in practical scenarios. Human activity in real world scenarios exhibits variation, resulting in skewness where identical activities are executed uniquely across clients. It leads to local model objectives drifting away from the global model objective, thereby impeding overall convergence. To address this challenge, we propose FedCoad, a novel federated model leveraging contrastive learning with adaptive control variates to handle the skewness among HAR clients. Model contrastive learning minimizes the gap in representation between global and local models to help global model convergence. During local model updates, the adaptive control variates penalize the local model updates with regard to the model weight and the rate of change from the control variates update. Our experiments show that FedCoad outperforms other state-of-the-art FL algorithms in HAR benchmark datasets.
Open peer comments: Debate/Discuss/Question/Opinion
<1>