Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Methodologies, Approaches, and Challenges in Parallel and Distributed Computing System
share announcement

Methodologies, Approaches, and Challenges in Parallel and Distributed Computing System

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (30 September 2023) | Viewed by 898

Special Issue Editor

Dr. Livia Marcellino

E-Mail Website
Guest Editor
Department of Science and Technology, University of Naples Parthenope, 80143 Napoli, Italy
Interests: computational science; numerical analysis; parallel scientific computing; domain decomposition parallel strategies; high-performance computing; parallel algorithms; parallel and distributed architectures; MPI-parallel and multi-many core architectures; GPU parallel computing; GP-GPU programming
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In the big data era, parallel computing is the most efficient way to solve large-size problems. By utilizing the parallel design of recent architectures, very sophisticated parallelization strategies can be realized and implemented in order to provide efficient parallel software.

This Special Issue aims to collect papers that present new parallel methods and algorithms for solving large-scale dimension problems for multi/many core, GPU and distributed architectures.

Dr. Livia Marcellino
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • parallel programming
  • parallel algorithms
  • cloud computing
  • parallel dynamical systems
  • distributed computing
  • GP-GPU computing
  • big data computing

Published Papers (1 paper)

Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

12 pages, 559 KiB  
Article
Federated Distillation Methodology for Label-Based Group Structures
by Geonhee Yang and Hyunchul Tae
Appl. Sci. 2024, 14(1), 277; https://doi.org/10.3390/app14010277 - 28 Dec 2023
Viewed by 560
Abstract
In federated learning (FL), clients train models locally without sharing raw data, ensuring data privacy. In particular, federated distillation transfers knowledge to clients regardless of the model architecture. However, when groups of clients with different label distributions exist, sharing the same knowledge among [...] Read more.
In federated learning (FL), clients train models locally without sharing raw data, ensuring data privacy. In particular, federated distillation transfers knowledge to clients regardless of the model architecture. However, when groups of clients with different label distributions exist, sharing the same knowledge among all clients becomes impractical. To address this issue, this paper presents an approach that clusters clients based on the output of a client model trained using their own data. The clients are clustered based on the predictions of their models for each label on a public dataset. Evaluations on MNIST and CIFAR show that our method effectively finds group identities, increasing accuracy by up to 75% over existing methods when the distribution of labels differs significantly between groups. In addition, we observed significant performance improvements on smaller client groups, bringing us closer to fair FL. Full article
(This article belongs to the Special Issue Methodologies, Approaches, and Challenges in Parallel and Distributed Computing System)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop