Atlas synchronization in the Hierarchical Federated Learning continuum
Publikationstyp
Conference Paper
Date Issued
2026-05
Sprache
English
Start Page
81
End Page
88
Citation
10th IEEE International Conference on Fog and Edge Computing, ICFEC 2026
Contribution to Conference
Publisher DOI
Scopus ID
Publisher
IEEE
ISBN of container
979-8-3315-7062-0
979-8-3315-7063-7
In Hierarchical Federated Learning (HFL), bandwidth budgets and delay constraints can prevent the timely synchronization of the semantic atlases (summaries) required for clients to learn unseen classes. Conventional synchronization policies typically optimize for geometric freshness. However, staleness becomes most harmful when it changes discrete curriculum gating decisions. We find that reducing feature space drift alone is an unreliable proxy for knowledge void recovery under constraints, because learning depends on decision consistency. Our Decision-Critical Atlas Synchronization (DCAS) policy prioritizes updates that are likely to alter these decisions and accelerates recovery from knowledge voids compared to a geometry-centric baseline.
Subjects
Prototypes
Clouds
Learning (artificial intelligence)
Printing
Federated learning
Modeling
Labeling
Synchronization
Planing
Equations
DDC Class
006.3: Artificial Intelligence