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

Along with the progress of AI democratization, neural networks are beingdeployed more frequently in edge devices for a wide range of applications.Fairness concerns gradually emerge in many applications, such as facerecognition and mobile medical. One fundamental question arises: what will bethe fairest neural architecture for edge devices? By examining the existingneural networks, we observe that larger networks typically are fairer. But,edge devices call for smaller neural architectures to meet hardwarespecifications. To address this challenge, this work proposes a novel Fairness-and Hardware-aware Neural architecture search framework, namely FaHaNa. Coupledwith a model freezing approach, FaHaNa can efficiently search for neuralnetworks with balanced fairness and accuracy, while guaranteed to meet hardwarespecifications. Results show that FaHaNa can identify a series of neuralnetworks with higher fairness and accuracy on a dermatology dataset. Targetedge devices, FaHaNa finds a neural architecture with slightly higher accuracy,5.28x smaller size, 15.14% higher fairness score, compared with MobileNetV2;meanwhile, on Raspberry PI and Odroid XU-4, it achieves 5.75x and 5.79xspeedup.

The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices