PENS: Leveraging Data Heterogeneity in Federated Learning

Visa enkel post
dc.contributor.authorOnoszko, Noa
dc.contributor.authorKarlsson, Gustav
dc.contributor.departmentChalmers tekniska högskola / Institutionen för matematiska vetenskapersv
dc.contributor.examinerGebäck, Tobias
dc.contributor.supervisorSchauer, Moritz
dc.contributor.supervisorListo Zec, Edvin
dc.date.accessioned2021-06-23T10:30:33Z
dc.date.available2021-06-23T10:30:33Z
dc.date.issued2021sv
dc.date.submitted2020
dc.description.abstractFederated learning (FL) is a decentralized machine learning technique where training is done cooperatively by exchanging model weights or gradients instead of sharing the raw data between the cooperating devices (clients). Classical FL algorithms such as federated averaging work best in the special case when the data is IID over clients. In this work, we address the problem of data heterogeneity in federated learning. We propose a decentralized federated learning (DFL) algorithm termed Performancebased Neighbour Selection Federated Learning Algorithm (PENS), that effectively leverages the data heterogeneity over clients. PENS is a cooperative communicationbased algorithm where clients communicate with other clients that have a similar data distribution. Specifically, model performance is used as a proxy for data similarity as no raw data is allowed to be shared among clients. Experiments on the CIFAR-10 dataset show that this communication scheme results in higher model accuracies than if clients communicate randomly with each other. The method is robust for different numbers of participating clients as long as the local datasets are sufficiently large.sv
dc.identifier.coursecodeMVEX03sv
dc.identifier.urihttps://hdl.handle.net/20.500.12380/302702
dc.language.isoengsv
dc.setspec.uppsokPhysicsChemistryMaths
dc.subjectdecentralized federated learning, federated learning, data heterogeneity, personalization, distributed machine learning, gossip learning, privacy, image classificationsv
dc.titlePENS: Leveraging Data Heterogeneity in Federated Learningsv
dc.type.degreeExamensarbete för masterexamensv
dc.type.uppsokH
local.programmeEngineering mathematics and computational science (MPENM), MSc
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
Master_thesis_Noa_Onozsko_och_Gustav Karlsson.pdf
Storlek:
2.98 MB
Format:
Adobe Portable Document Format
Beskrivning:
Ladda ner
License bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
license.txt
Storlek:
1.14 KB
Format:
Item-specific license agreed upon to submission
Beskrivning:
Ladda ner
Samling
Examensarbeten för masterexamen