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 allows training of data stored in distributed deviceswithout the need for centralizing training data, thereby maintaining dataprivacy. Addressing the ability to handle data heterogeneity (non-identical andindependent distribution or non-IID) is a key enabler for the wider deploymentof Federated Learning. In this paper, we propose a novel Divide-and-Conquertraining methodology that enables the use of the popular FedAvg aggregationalgorithm by overcoming the acknowledged FedAvg limitations in non-IIDenvironments. We propose a novel use of Cosine-distance based Weight Divergencemetric to determine the exact point where a Deep Learning network can bedivided into class agnostic initial layers and class-specific deep layers forperforming a Divide and Conquer training. We show that the methodology achievestrained model accuracy at par (and in certain cases exceeding) with numbersachieved by state-of-the-art Aggregation algorithms like FedProx, FedMA, etc.Also, we show that this methodology leads to compute and bandwidthoptimizations under certain documented conditions.

Weight Divergence Driven Divide-and-Conquer Approach for Optimal Federated Learning from non-IID Data