Ph.D. in Ingegneria Informatica E Dei Sistemi , 38th cycle (2022-2025)
Ph.D. obtained in 2026
Dissertation:
Distributed and Federated Learning over IoT networks (Abstract)
Tutors:
Andrea Calimera Enrico Macii
Research presentation:
PosterProfile
Research topic
Distributed and Federated Learning over IoT networks
Keywords
Biography
Within this context, distributed and federated learning paradigms represent an effective and scalable approach for training deep learning models directly over decentralized data. His work primarily focuses on optimizing Federated Learning (FL) strategies to reduce synchronization overhead and maximize the efficient use of the limited computational, communication, and energy resources available on low-power IoT nodes.
He focuses on designing dynamic workflows for convergence-aware and budget-constrained training, maintaining accuracy and efficiency in resource-limited environments.
Beyond these core objectives, his research also addresses broader challenges, including the data and system heterogeneity inherent in cross-device settings, emerging security and privacy threats that undermine the confidentiality and robustness of implementations, and the need to reduce reliance on costly human supervision for decentralized data annotation. By addressing these challenges through general and practical solutions, he promotes the deployment of IoT knowledge exchange in an efficient, privacy-conscious, and robust fashion. His long-term ambition is to pave the way for the large-scale adoption of ubiquitous intelligent services.
Awards and Honors
- Certificate of attendance to conference as a speaker at the IEEE International Symposium on Low Power Electronics and Design (ISLPED) 2023. (2023)
- Certificate of attendance to conference as a speaker at the 31st IEEE International Conference on Electronics Circuits and Systems (ICECS), 2024. (2024)
- Certificate of attendance to conference as a speaker at the IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC), 2025 (2025)
- Certificate of participation as a session chair at the conference IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC), 2025. Session chair for: 2025 IEEE COMPSAC International Workshop on Modeling and Verifying Distributed-Embedded Applications (MVDA 2025) 2025 IEEE International Workshop on Rising ICT Solutions for Smart Grids as Multi-energy Systems (ICT4SmartGrid 2025) (2025)
- Certificate of presentation at the International Joint Conference on Neural Networks (IJCNN) 2025. (2025)
- PhD DAUIN Quality Award 2025 (2025)
Teaching
Teachings
Bachelor of Science
- Informatica. A.A. 2024/25, INGEGNERIA AEROSPAZIALE. Collaboratore del corso
- Informatica. A.A. 2022/23, INGEGNERIA INFORMATICA. Collaboratore del corso
- Informatica. A.A. 2023/24, INGEGNERIA INFORMATICA. Collaboratore del corso
- Informatica. A.A. 2025/26, INGEGNERIA AEROSPAZIALE. Collaboratore del corso
Research
Research groups
Publications
Works published during the Ph.D. View all publications in Porto@Iris
- Malan, Erich; Peluso, Valentino; Calimera, Andrea; Macii, Enrico (2026)
FedAGF: Adaptive Concurrency via Gradient Feedback for Mitigating Extreme Label Skew in Budget-Constrained Federated Learning. In: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS. I, REGULAR PAPERS, vol. 73, pp. 3835-3848. ISSN 1549-8328
Contributo su Rivista - Malan, Erich; Peluso, Valentino; Calimera, Andrea; Macii, Enrico (2026)
Refined Two-Sided Learning Rate Tuning for Robust Evaluation in Federated Learning. In: IEEE TRANSACTIONS ON ARTIFICIAL INTELLIGENCE, vol. 7, pp. 906-917. ISSN 2691-4581
Contributo su Rivista - Malan, Erich (2026)
Distributed and Federated Learning over IoT networks. relatore: CALIMERA, ANDREA; MACII, Enrico; , 38. XXXVIII Ciclo, P.: 183
Doctoral Thesis - Malan, Erich; De Vizia, Claudia; Castangia, Marco; Peluso, Valentino; Calimera, Andrea; ... (2025)
Privacy-Preserving Federated Learning for Household Characteristic Identification. In: 2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC), Toronto ON (CAN), 08-11 July 2025, pp. 2040-2045. ISBN: 979-8-3315-7434-5
Contributo in Atti di Convegno (Proceeding) - Malan, Erich; Peluso, Valentino; Calimera, Andrea; Macii, Enrico (2025)
Adaptive Client Participation in Budget-Constrained Federated Learning with Extreme Label Skew. In: 2025 23rd IEEE Interregional NEWCAS Conference (NEWCAS), Paris (FRA), 22-25 June 2025, pp. 15-19. ISBN: 979-8-3315-3256-7
Contributo in Atti di Convegno (Proceeding) - Malan, Erich; Peluso, Valentino; Calimera, Andrea; Macii, Enrico (2025)
Gradient-Aware Participation for Energy Reduction in Federated Learning with Extreme Label Skew. In: International Joint Conference on Neural Networks (IJCNN), Rome (ITA), June 30-July 5, 2025. ISBN: 979-8-3315-1042-8
Contributo in Atti di Convegno (Proceeding) - Malan, Erich; Peluso, Valentino; Calimera, Andrea; Macii, Enrico; Montuschi, Paolo (2024)
Automatic Layer Freezing for Communication Efficiency in Cross-Device Federated Learning. In: IEEE INTERNET OF THINGS JOURNAL, vol. 11, pp. 6072-6083. ISSN 2327-4662
Contributo su Rivista - Peluso, Valentino; Malan, Erich; Calimera, Andrea; Macii, Enrico (2024)
Private Tensor Freezing for an Efficient Federated Learning with Homomorphic Encryption. In: International Conference on Computer Design (ICCD) 2024, Milan (ITA), 18-20 November 2024, pp. 308-315. ISBN: 979-8-3503-8040-8
Contributo in Atti di Convegno (Proceeding) - Malan, Erich; Peluso, Valentino; Calimera, Andrea; Macii, Enrico (2024)
Draft & Refine: Efficient Resource Management in Federated Learning under Pathological Labels Skew. In: International Conference on Electronics Circuits and Systems (ICECS) 2024, Nancy (FRA), 18-20 November 2024, pp. 1-4. ISBN: 979-8-3503-7720-0
Contributo in Atti di Convegno (Proceeding) - Malan, Erich; Peluso, Valentino; Calimera, Andrea; Macii, Enrico (2023)
Enabling DVFS Side-Channel Attacks for Neural Network Fingerprinting in Edge Inference Services. In: International Symposium on Low Power Electronics and Design, Vienna (AUT), 07-08 August 2023, pp. 1-6. ISBN: 979-8-3503-1175-4
Contributo in Atti di Convegno (Proceeding) - Malan, Erich; Peluso, Valentino; Calimera, Andrea; Macii, Enrico (2023)
Communication-Efficient Federated Learning with Gradual Layer Freezing. In: IEEE EMBEDDED SYSTEMS LETTERS, vol. 15, pp. 25-28. ISSN 1943-0663
Contributo su Rivista