Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 3
Review and comparative evaluation of resource-adaptive collaborative training for heterogeneous edge devices
Boris Radovič, Marco Canini, Veljko Pejović
Izvirni znanstveni članek
Oznake: zvezno učenje;porazdeljeno učenje;vseprisotno računalništvo;mobilno računalništvo;federated learning;split learning;distributed collaborative learning;ubiquitous and mobile computing;device heterogeneity;
Growing concerns about centralized mining of personal data threatens to stifle further proliferation of machine learning (ML) applications. Consequently, a recent trend in ML training advocates for a paradigm shift – moving the computation of ML models from a centralized server to a federation of ed ...
Leto: 2025 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Train your cake and eat it too! Repurposing collaborative training to tailor LLMs to private data without sharing
Boris Radovič, Mohammed Aljahdali, Marco Canini, Veljko Pejović, Zuhair Khayyat
Objavljeni znanstveni prispevek na konferenci
Oznake: poraba energije;digitalni podatki;energy usage;digital data;
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 th ...
Leto: 2024 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Towards a unified framework for split learning
Boris Radovič, Marco Canini, Samuel Horváth, Veljko Pejović, Praneeth Vepakomma
Objavljeni znanstveni prispevek na konferenci
Oznake: porazdeljeno učenje;strojno učenje;zvezno učenje;split learning;machine learning;federated learning;
Split Learning (SL) is a principled approach for training models on data distributed across multiple devices without sharing training data. While SL emerged as an alternative to federated learning to reduce the compute burden on devices, it also enables a more fair redistribution of work between edg ...
Leto: 2025 Vir: Fakulteta za računalništvo in informatiko (UL FRI)
Št. zadetkov: 3
Ključne besede:
Leto izdaje:
Avtorji:
Repozitorij:
Tipologija:
Jezik: