Details

Train your cake and eat it too! Repurposing collaborative training to tailor LLMs to private data without sharing
ID Radovič, Boris (Author), ID Aljahdali, Mohammed (Author), ID Canini, Marco (Author), ID Pejović, Veljko (Author), ID Khayyat, Zuhair (Author)

.pdfPDF - Presentation file, Download (374,25 KB)
MD5: E45BC051716C6DCC50601F8294586511
URLURL - Source URL, Visit https://openreview.net/forum?id=FGupKd365r This link opens in a new window

Abstract
In the emerging field of large language models (LLMs), a significant challenge arises when organizations with vast datasets lack the computational resources to independently train and fine-tune models. This issue stems from privacy, compliance, and resource constraints: organizations cannot share their sensitive data but still need external computational assistance for model training. In this paper, we implement, enhance, and empirically compare several methods, including Split Learning (SL) and select Federated Learning (FL) methods, which enable data-rich yet compute-poor clients to offload LLM training without sharing raw data. Our study evaluates these methods across multiple dimensions, including model quality and training time.

Language:English
Keywords:energy usage, digital data
Work type:Other
Typology:1.08 - Published Scientific Conference Contribution
Organization:FRI - Faculty of Computer and Information Science
Publication status:Published
Publication version:Version of Record
Year:2024
Number of pages:Str. 1-10
PID:20.500.12556/RUL-166792 This link opens in a new window
UDC:004
COBISS.SI-ID:221660675 This link opens in a new window
Copyright:
Licenca Creative Commons je navedena na pristajalni strani članka (glej izvorni URL): "Licensed under Crative Commons Atribution 4.0 International". (Datum opombe 24. 1. 2025)
Publication date in RUL:24.01.2025
Views:148
Downloads:81
Metadata:XML DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Record is a part of a monograph

Title:Workshop on Efficient Systems for Foundation Models II : ES-FoMo-II 2024
Place of publishing:[Massachusetts
Publisher:OpenReview
Year:2024
COBISS.SI-ID:221659651 This link opens in a new window

Licences

License:CC BY 4.0, Creative Commons Attribution 4.0 International
Link:http://creativecommons.org/licenses/by/4.0/
Description:This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

Language:Slovenian
Keywords:poraba energije, digitalni podatki

Projects

Funder:Other - Other funder or multiple funders
Name:SDAIA-KAUST AI

Funder:ARRS - Slovenian Research Agency
Project number:J2-3047
Name:Kontekstno-odvisno približno računanje na mobilnih napravah

Funder:ARRS - Slovenian Research Agency
Project number:P2-0098
Name:Računalniške strukture in sistemi

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back