Ricerca | Uncategorized

Call for Papers – Workshop FLEdge-AI @ ACM MOBICOM 2025

Commenta



Maggio 25, 2025



Comments (0)



By Francesco Piccialli

Link: https://edgeai2025.github.io

Overview

The FLEdge-AI 2025 workshop aims to bring together researchers, practitioners, and industry leaders to explore the critical intersection of Federated Learning (FL), Edge AI, privacy, and mobility. As the mobile computing landscape rapidly evolves towards 6G, pervasive edge intelligence, and decentralized AI, FL and Edge AI are emerging as foundational technologies. They enable privacy-preserving, resilient, and distributed machine learning across dynamic, resource-constrained, and heterogeneous environments. This workshop will serve as a premier forum for discussing the latest research in algorithms, systems, and real-world deployments of federated learning and edge AI in mobile and wireless scenarios. We aim to address the pressing technical challenges and opportunities in making FL and Edge AI practical and impactful for mobile users and applications. Key issues include communication bottlenecks in mobile systems, device and statistical heterogeneity, user mobility and dynamic network topologies, and ensuring robust privacy and security in open and untrusted environments. The goal is to foster innovations that bridge the gap between theory and deployment, particularly focusing on how these technologies can operate effectively under the constraints of mobile networks and edge devices.

TPC and General Chairs

Francesco Piccialli (University of Naples Federico II, Italy)
David Camacho (Universidad Politécnica de Madrid, Spain)
Fabio Giampaolo (University of Naples Federico II, Italy)
Jon Crowcroft (University of Cambridge, UK)
Liu Wang (Hong Kong Polytechnic University, China)
Yuchao Zhang (Beijing University of Posts and Telecommunications, China)

Workshop Topics

The goal of this FLEdge-AI 2025 Workshop is to bring together scientists, researchers, and engineers to identify new problems, latest novel topics, and emerging technologies. We focus on all aspects of edge network, data privacy and federated technologies, including but not limited to the following:

Federated Learning protocols for mobile, vehicular, and edge networks
Communication-efficient FL (e.g., quantization, sparsification, gossip-based)
FL under client mobility, heterogeneity, and intermittent connectivity
Privacy and security in mobile FL (e.g., differential privacy, secure aggregation)
Personalization and federated transfer learning
Multi-agent and swarm intelligence-based FL
Benchmarking FL in wireless/mobile environments
Network-aware optimization and system-level co-design for FL
FL deployment in UAVs, mobile edge clouds, and autonomous systems