4 papers
From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning
Huong Nguyen, Mickaël Bettinelli, Amirhossein Ghaffari +4
Federated Learning (FL) has emerged as a promising solution for data hunger in centralized learning. This paradigm enables privacy with multiple clients to train a shared-task mode…
UserCentrix: An Agentic Memory-augmented AI Framework for Smart Spaces
Alaa Saleh, Sasu Tarkoma, Praveen Kumar Donta +5
Agentic Artificial Intelligence (AI) constitutes a transformative paradigm in the evolution of intelligent agents and decision-support systems, redefining smart environments by enh…
Agentic TinyML for Intent-aware Handover in 6G Wireless Networks
Alaa Saleh, Roberto Morabito, Sasu Tarkoma +3
As 6G networks evolve into increasingly AI-driven, user-centric ecosystems, traditional reactive handover mechanisms demonstrate limitations, especially in mobile edge computing an…
Graph-based Gossiping for Communication Efficiency in Decentralized Federated Learning
Huong Nguyen, Hong-Tri Nguyen, Praveen Kumar Donta +2
Federated learning has emerged as a privacy-preserving technique for collaborative model training across heterogeneously distributed silos. Yet, its reliance on a single central se…