English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Federated Learning (FL) enables distributed training of machine learningmodels while keeping personal data on user devices private. While we witnessincreasing applications of FL in the area of mobile sensing, such as humanactivity recognition (HAR), FL has not been studied in the context of amulti-device environment (MDE), wherein each user owns multiple data-producingdevices. With the proliferation of mobile and wearable devices, MDEs areincreasingly becoming popular in ubicomp settings, therefore necessitating thestudy of FL in them. FL in MDEs is characterized by being not independent andidentically distributed (non-IID) across clients, complicated by the presenceof both user and device heterogeneities. Further, ensuring efficientutilization of system resources on FL clients in a MDE remains an importantchallenge. In this paper, we propose FLAME, a user-centered FL trainingapproach to counter statistical and system heterogeneity in MDEs, and bringconsistency in inference performance across devices. FLAME features (i)user-centered FL training utilizing the time alignment across devices from thesame user; (ii) accuracy- and efficiency-aware device selection; and (iii)model personalization to devices. We also present an FL evaluation testbed withrealistic energy drain and network bandwidth profiles, and a novel class-baseddata partitioning scheme to extend existing HAR datasets to a federated setup.Our experiment results on three multi-device HAR datasets show that FLAMEoutperforms various baselines by 4.3-25.8% higher F1 score, 1.02-2.86x greaterenergy efficiency, and up to 2.06x speedup in convergence to target accuracythrough fair distribution of the FL workload.

FLAME: Federated Learning Across Multi-device Environments