Federated Learning with Heterogeneous Labels and Models for Mobile Activity Monitoring

12/04/2020
by   Gautham Krishna Gudur, et al.
4

Various health-care applications such as assisted living, fall detection, etc., require modeling of user behavior through Human Activity Recognition (HAR). Such applications demand characterization of insights from multiple resource-constrained user devices using machine learning techniques for effective personalized activity monitoring. On-device Federated Learning proves to be an effective approach for distributed and collaborative machine learning. However, there are a variety of challenges in addressing statistical (non-IID data) and model heterogeneities across users. In addition, in this paper, we explore a new challenge of interest – to handle heterogeneities in labels (activities) across users during federated learning. To this end, we propose a framework for federated label-based aggregation, which leverages overlapping information gain across activities using Model Distillation Update. We also propose that federated transfer of model scores is sufficient rather than model weight transfer from device to server. Empirical evaluation with the Heterogeneity Human Activity Recognition (HHAR) dataset (with four activities for effective elucidation of results) on Raspberry Pi 2 indicates an average deterministic accuracy increase of at least  11.01 on-device capabilities of our proposed framework.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/06/2020

Resource-Constrained Federated Learning with Heterogeneous Labels and Models

Various IoT applications demand resource-constrained machine learning me...
research
06/18/2021

Zero-Shot Federated Learning with New Classes for Audio Classification

Federated learning is an effective way of extracting insights from diffe...
research
11/02/2020

Semi-supervised Federated Learning for Activity Recognition

The proliferation of IoT sensors and edge devices makes it possible to u...
research
05/31/2019

ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition

Various health-care applications such as assisted living, fall detection...
research
10/19/2021

A Federated Learning Aggregation Algorithm for Pervasive Computing: Evaluation and Comparison

Pervasive computing promotes the installation of connected devices in ou...
research
03/24/2021

Opportunistic Federated Learning: An Exploration of Egocentric Collaboration for Pervasive Computing Applications

Pervasive computing applications commonly involve user's personal smartp...
research
05/31/2021

Meta-HAR: Federated Representation Learning for Human Activity Recognition

Human activity recognition (HAR) based on mobile sensors plays an import...

Please sign up or login with your details

Forgot password? Click here to reset