https://www.mdu.se/

mdu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Hyperparameters Optimization for Federated Learning System: Speech Emotion Recognition Case Study
Mälardalens universitet, Akademin för innovation, design och teknik, Inbyggda system.
2023 (Engelska)Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

Federated Learning (FL) has emerged as a promising, massively distributed way to train a joint deep model across numerous edge devices, ensuring user data privacy by retaining it on the device. In FL, Hyperparameters (HP) significantly affect the training overhead regarding computation and transmission time, computation and transmission load, as well as model accuracy. This paper presents a novel approach where Hyperparameters Optimization (HPO) is used to optimize the performance of the FL model for Speech Emotion Recognition (SER) application. To solve this problem, both Single-Objective Optimization (SOO) and Multi-Objective Optimization (MOO) models are developed and evaluated. The optimization model includes two objectives: accuracy and total execution time. Numerical results show that optimal Hyperparameters (HP) settings allow for improving both the accuracy of the model and its computation time. The proposed method assists FL system designers in finding optimal parameters setup, allowing them to carry out model design and development efficiently depending on their goals. 

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers (IEEE), 2023.
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:mdh:diva-64361ISI: 001103180200011ISBN: 9798350316971 (digital)ISBN: 9798350316988 (tryckt)OAI: oai:DiVA.org:mdh-64361DiVA, id: diva2:1800428
Konferens
The Eighth IEEE International Conference on Fog and Mobile Edge Computing, FMEC 2023,Tartu, Estonia. September 18-20, 2023
Tillgänglig från: 2023-09-26 Skapad: 2023-09-26 Senast uppdaterad: 2026-06-12Bibliografiskt granskad
Ingår i avhandling
1. Balancing Privacy and Performance in Emerging Applications of Federated Learning
Öppna denna publikation i ny flik eller fönster >>Balancing Privacy and Performance in Emerging Applications of Federated Learning
2023 (Engelska)Licentiatavhandling, sammanläggning (Övrigt vetenskapligt)
Abstract [en]

Federated Learning (FL) has emerged as a novel paradigm within machine learning (ML) that allows multiple devices to collaboratively train a shared ML model without sharing their private data with a central server. FL has gained popularity across various applications by eliminating the necessity for centralized data storage, thereby improving the confidentiality of sensitive information. Among the new FL applications, this thesis focuses on Speech Emotion Recognition (SER), which involves the analysis of audio signals from human speech to identify patterns and classify the conveyed emotions. When SER is implemented within a FL framework, even though speech data remains on local devices, new privacy challenges emerge during the training phase and the exchange of SER model update parameters between servers and clients. These challenges encompass the potential for privacy leakage and adversarial attacks, including model inversion attacks and membership or property inference attacks, which can be conducted by unauthorized or malicious parties to exploit the shared SER model, compromising client data confidentiality and revealing sensitive information.

While several privacy-preserving solutions have been developed to mitigate potential breaches in FL architectures, those are too generic to be easily integrated into specific applications. Furthermore, incorporating existing privacy-preserving mechanisms into the FL framework can increase communication and computational overheads, which may, in turn, compromise data utility and learning performance.

This thesis aims to propose privacy-preserving methods in FL for emerging security-critical applications such as SER while addressing the challenges related to their effect on performance. First, we categorize and analyze recent research on privacy-preserving mechanisms in FL, with a focus on assessing their effects on FL performance and how to balance privacy and performance across various applications. Second, we design an optimized FL setup tailored to SER applications in order to evaluate effects on performance and overhead. Third, we design and develop privacy-preserving mechanisms within FL to safeguard against potential privacy threats while ensuring the confidentiality of clients' data. Finally, we propose and evaluate new methods for FL in SER and integrate them with appropriate privacy-preserving mechanisms to achieve an optimal balance of privacy with efficiency, accuracy, as well as communication and computation overhead.

Ort, förlag, år, upplaga, sidor
Västerås: Mälardalens universitet, 2023
Serie
Mälardalen University Press Licentiate Theses, ISSN 1651-9256 ; 349
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
datavetenskap
Identifikatorer
urn:nbn:se:mdh:diva-64679 (URN)978-91-7485-621-7 (ISBN)
Presentation
2023-12-14, Paros, Mälardalens universitet, Västerås, 13:00 (Engelska)
Opponent
Handledare
Tillgänglig från: 2023-11-07 Skapad: 2023-11-06 Senast uppdaterad: 2025-10-10Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Person

Mohammadi, Samaneh

Sök vidare i DiVA

Av författaren/redaktören
Mohammadi, Samaneh
Av organisationen
Inbyggda system
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

isbn
urn-nbn

Altmetricpoäng

isbn
urn-nbn
Totalt: 364 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf