Publications by the same author
plus in the repository
plus in Google Scholar

Bibliografische Daten exportieren
 

CollaFuse: Navigating Limited Resources and Privacy in Collaborative Generative AI

DOI zum Zitieren der Version auf EPub Bayreuth: https://doi.org/10.15495/EPub_UBT_00007511
URN to cite this document: urn:nbn:de:bvb:703-epub-7511-6

Title data

Zipperling, Domenique ; Allmendinger, Simeon ; Struppek, Lukas ; Kühl, Niklas:
CollaFuse: Navigating Limited Resources and Privacy in Collaborative Generative AI.
2024
Event: The 32nd European Conference on Information Systems (ECIS) , 13.06 - 19.06.2024 , Paphos, Cyprus.
(Conference item: Conference , Paper )

[thumbnail of CollaFuse.pdf]
Format: PDF
Name: CollaFuse.pdf
Version: Published Version
Available under License Creative Commons BY-NC-ND 4.0: Attribution, Noncommercial, No Derivative Works
Download (409kB)

Abstract

In the landscape of generative artificial intelligence, diffusion-based models present challenges for socio-technical systems in data requirements and privacy. Traditional approaches like federated learning distribute the learning process but strain individual clients, especially with constrained resources (e.g., edge devices). In response to these challenges, we introduce CollaFuse, a novel framework inspired by split learning. Tailored for efficient and collaborative use of denoising diffusion probabilistic models, CollaFuse enables shared server training and inference, alleviating client computational burdens. This is achieved by retaining data and computationally inexpensive GPU processes locally at each client while outsourcing the computationally expensive processes to the shared server. Demonstrated in a healthcare context, CollaFuse enhances privacy by highly reducing the need for sensitive information sharing. These capabilities hold the potential to impact various application areas, such as the design of edge computing solutions, healthcare research, or autonomous driving. In essence, our work advances distributed machine learning, shaping the future of collaborative GenAI networks.

Further data

Item Type: Conference item (Paper)
Keywords: Generative Models; Distributed Learning; Split Learning; Diffusion Model
DDC Subjects: 000 Computer Science, information, general works > 004 Computer science
600 Technology, medicine, applied sciences > 600 Technology
Institutions of the University: Faculties > Faculty of Law, Business and Economics > Department of Business Administration > Chair Information Systems Management > Chair Information Systems Management - Univ.-Prof. Dr.-Ing. Niklas Kühl
Faculties
Faculties > Faculty of Law, Business and Economics
Faculties > Faculty of Law, Business and Economics > Department of Business Administration
Faculties > Faculty of Law, Business and Economics > Department of Business Administration > Chair Information Systems Management
Language: English
Originates at UBT: Yes
URN: urn:nbn:de:bvb:703-epub-7511-6
Date Deposited: 02 Apr 2024 08:26
Last Modified: 02 Apr 2024 08:27
URI: https://epub.uni-bayreuth.de/id/eprint/7511

Downloads

Downloads per month over past year