Decentralized Deep Learning under Distributed Concept Drift: A Novel Approach to Dealing with Changes in Data Distributions Over Clients and Over Time

Visa enkel post
dc.contributor.authorKlefbom, Emilie
dc.contributor.authorÖrtenberg Toftås, Marcus
dc.contributor.departmentChalmers tekniska högskola / Institutionen för matematiska vetenskapersv
dc.contributor.examinerModin, Klas
dc.contributor.supervisorDubhashi, Devdatt
dc.date.accessioned2023-08-30T12:50:22Z
dc.date.available2023-08-30T12:50:22Z
dc.date.issued2023
dc.date.submitted2023
dc.description.abstractIn decentralized deep learning, clients train local models in a peer-to-peer fashion by sharing model parameters, rather than data. This allows collective model training in cases where data may be sensitive or for other reasons unable to be transferred. In this setting, variations in data distributions across clients have been extensively studied, however, variations over time have received no attention. This project proposes a solution to address decentralized learning where the data distributions vary both across clients and over time. We propose a novel algorithm that can adapt to the evolving concepts in the network without any prior knowledge or estimation of the number of concepts. Evaluation of the algorithm is done using standard benchmarks adapted to the temporal setting, where it outperforms previous methods for decentralized learning.
dc.identifier.coursecodeMVEX03
dc.identifier.urihttp://hdl.handle.net/20.500.12380/306955
dc.language.isoeng
dc.setspec.uppsokPhysicsChemistryMaths
dc.subjectFederated Learning, Decentralized Learning, Machine Learning, Data Heterogeneity, Non-IID, Personalization, Concept Drift
dc.titleDecentralized Deep Learning under Distributed Concept Drift: A Novel Approach to Dealing with Changes in Data Distributions Over Clients and Over Time
dc.type.degreeExamensarbete för masterexamensv
dc.type.degreeMaster's Thesisen
dc.type.uppsokH
local.programmeComplex adaptive systems (MPCAS), MSc
local.programmeData science and AI (MPDSC), MSc
Ladda ner
Original bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
Master_Thesis_Marcus_Toftås_Emilie_Klefbom_2023.pdf
Storlek:
5.75 MB
Format:
Adobe Portable Document Format
Beskrivning:
Ladda ner
License bundle
Visar 1 - 1 av 1
Bild (thumbnail)
Namn:
license.txt
Storlek:
2.35 KB
Format:
Item-specific license agreed upon to submission
Beskrivning:
Ladda ner
Samling
Examensarbeten för masterexamen