Efficient federated learning for distributed neuroimaging data
Thapaliya B, Ohib R, Geenjaar E, Liu J, Calhoun V, Plis S. Efficient federated learning for distributed neuroimaging data. Frontiers In Neuroinformatics 2024, 18: 1430987. PMID: 39315000, PMCID: PMC11416982, DOI: 10.3389/fninf.2024.1430987.Peer-Reviewed Original ResearchFederated learningCommunication overheadsSparse modelModel sparsityClient siteTraining phaseAdolescent Brain Cognitive DevelopmentData sharingEfficient communicationLarge modelsLocal trainingResource capabilitiesDatasetCommunicationLearningSparsityActual dataOverheadsPrivacyNeuroimaging dataCognitive developmentDataScientific communitySharingDecentralized Mixed Effects Modeling in COINSTAC
Basodi S, Raja R, Gazula H, Romero J, Panta S, Maullin-Sapey T, Nichols T, Calhoun V. Decentralized Mixed Effects Modeling in COINSTAC. Neuroinformatics 2024, 22: 163-175. PMID: 38424371, DOI: 10.1007/s12021-024-09657-7.Peer-Reviewed Original ResearchLarge-scale analysis of dataDecentralized platformLow bandwidthData transferMemory requirementsData sharingSubstantial overheadsCOINSTACStructural magnetic resonance imagingNeuroimaging communityDataData poolNeuroimaging analysisOverheadsPrivacyLarge-scale analysisImagesMagnetic resonance imagingGray matter reductionsMedial frontal regionsDimensionalityLinear mixed-effectsModeling approachBandwidthResearch groups