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

Although Federated Learning (FL) is promising to enable collaborativelearning among Artificial Intelligence of Things (AIoT) devices, it suffersfrom the problem of low classification performance due to various heterogeneityfactors (e.g., computing capacity, memory size) of devices and uncertainoperating environments. To address these issues, this paper introduces aneffective FL approach named AdaptiveFL based on a novel fine-grained width-wisemodel pruning strategy, which can generate various heterogeneous local modelsfor heterogeneous AIoT devices. By using our proposed reinforcementlearning-based device selection mechanism, AdaptiveFL can adaptively dispatchsuitable heterogeneous models to corresponding AIoT devices on the fly based ontheir available resources for local training. Experimental results show that,compared to state-of-the-art methods, AdaptiveFL can achieve up to 16.83%inference improvements for both IID and non-IID scenarios.

AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems