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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Federated learning (FL) is a decentralized machine learning approach whereindependent learners process data privately. Its goal is to create a robust andaccurate model by aggregating and retraining local models over multiple rounds.However, FL faces challenges regarding data heterogeneity and model aggregationeffectiveness. In order to simulate real-world data, researchers use methodsfor data partitioning that transform a dataset designated for centralizedlearning into a group of sub-datasets suitable for distributed machine learningwith different data heterogeneity. In this paper, we study the currentlypopular data partitioning techniques and visualize their main disadvantages:the lack of precision in the data diversity, which leads to unreliableheterogeneity indexes, and the inability to incrementally challenge the FLalgorithms. To resolve this problem, we propose a method that leverages entropyand symmetry to construct 'the most challenging' and controllable datadistributions with gradual difficulty. We introduce a metric to measure dataheterogeneity among the learning agents and a transformation technique thatdivides any dataset into splits with precise data diversity. Through acomparative study, we demonstrate the superiority of our method over existingFL data partitioning approaches, showcasing its potential to challenge modelaggregation algorithms. Experimental results indicate that our approachgradually challenges the FL strategies, and the models trained on FedSymdistributions are more distinct.

FedSym: Unleashing the Power of Entropy for Benchmarking the Algorithms for Federated Learning