Summary
Post‑doc at the Department of Computer Science and Engineering (DISI) – University of Bologna. My research is focused on decentralized learning
techniques, such as Federated Learning.
Education
PhD in Computer Science and Engineering, University of Bologna Nov. 2019 ‑ March 2023
PhD Thesis: Concepts and Methods for Efficient Decentralized Learning
Master Degree in Computer Engineering, University of Bologna Sep. 2016 ‑ March 2019
Final Mark: 110/110
Master Thesis: Mobile Computation Offloading on Android: Evaluation of Sockets and Native Code Offloading Opportunities
Bachelor Degree in Computer Engineering, University of Bologna Sep. 2012 ‑ July 2016
Publications
Paolo Bellavista, Luca Foschini, and Alessio Mora. 2021. Decentralised Learning in Federated Deployment Environments: A System‑Level Survey.
ACM Comput. Surv. 54, 1, Article 15 (January 2021), 38 pages. DOI: https://doi.org/10.1145/3429252
Alessio Mora, Irene Tenison, Paolo Bellavista, and Irina Rish. Knowledge distillation for federated learning: a practical guide. arXiv preprint
arXiv:2211.04742 (2022).
Nicolò Romandini, Alessio Mora, Carlo Mazzocca, Rebecca Montanari, and Paolo Bellavista. Federated Unlearning: A Survey on Methods, Design
Guidelines, and Evaluation Metrics. arXiv preprint arXiv:2401.05146 (2024).
Paolo Bellavista, Luca Foschini, and Alessio Mora. Communication‑efficient Heterogeneouse Federated Dropout in Cross‑device Settings. GLOBECOM
2021 ‑ 2021 IEEE Global Communications Conference, 2021, pp. 1‑6. DOI: 10.1109/GLOBECOM46510.2021.9685710.
Alessio Mora, Luca Foschini and Paolo Bellavista. Structured Sparse Ternary Compression for Convolutional Layers in Federated Learning. 2022
IEEE 95th Vehicular Technology Conference: (VTC2022‑Spring), 2022, pp. 1‑5, DOI: 10.1109/VTC2022‑Spring54318.2022.9860833.
Alessio Mora, Davide Fantini, Paolo Bellavista. Federated Learning Algorithms with Heterogeneous Data Distributions: An Empirical Evaluation.
2022 IEEE/ACM 7th Symposium on Edge Computing (SEC). IEEE, 2022.
Alessandro Buratto, Alessio Mora, Armir Bujari, and Leonardo Badia. Game Theoretic Analysis of AoI Efficiency for Participatory and Federated
Data Ecosystems. 2023 IEEE International Conference on Communications Workshops (ICC Workshops) (pp. 1301‑1306).
Paolo Bellavista and Alessio Mora. Edge Cloud as an Enabler for Distributed AI in Industrial IoT Applications: the Experience of the IoTwins Project.
In: AI&IoT@ AI* IA. 2019. p. 1‑15.
Work Experience
Visiting Researcher, MILA, University of Montreal June 2022 ‑ Sept. 2022
• Worked in professor Irina’s Rish research group.
• Worked on Federated Learning optimizations strategies to reduce the communication cost of the process, and/or to deal with heterogeneous
data, and/or to enable model‑agnostic FL.
Research Assistant, University of Bologna, DISI April 2019 ‑ Nov. 2019
• Started my research in the field of Federated Learning. Worked on the seminal version of the survey later published in ACM CSUR.
Junior Computer Engineer, Sorbonne University, LIP6 Oct. 2018 ‑ March 2019
• Worked on computation offloading for Android devices within the ULOOF project under the supervision of professor Stefano Secci. I have
worked with the Java language, and directly with the Java bytecode to inject the logic for triggering the offloading process directly inside the
APK of Android Apps.
Intern, University of Bologna, DISI April 2016 ‑ May 2016
• Developed a computer vision application, using libraries such as OpenCV and PointCloudLibrary, that visualizes point clouds in 3 dimensions
starting from a depth image.
Awards
Summer of Reproducibility Award – Flower Labs (flower.dev) November 2023
Awarded $2,000.00 USD for your contribution to advancing the state of reproducibility in the field of federated learning. Implemented a stateof‑the‑art
baseline ”FedMLB: Multi‑Level Branched Regularization for Federated Learning” in Flower (flower.dev), and reproduced the results of
the original paper. Github repository.
Peer‑Reviewing Service
My activity as peer reviewer for journals is tracked in my Publons profile.
I have reviewed a number of journal papers (e.g., ACM Transactions on Intelligent Systems and Technology, IEEE Communications Magazine, IEEE
Internet of Things Journal, IEEE Intelligent Systems, Wireless Networks (Springer Nature) and others) and of conference papers (e.g., ACM MSWiM,
IEEE GLOBECOM).
I served as Chair for the Session titled Internet of Things and Sensor Networks (IoTSN) at IEEE GLOBECOM 2021.
European Projects
During my experience as a researcher at the Dept. of Computer Science and Engineering of the University of Bologna, I have been involved in
ontology‑based projects funded by the European Union.
OntoTrans April 2020 ‑ Today
OntoTrans (ontology‑based Open Translation Environment). The aim of the project is to enable end users to represent in a standard ontological
form their manufacturing process challenges and to connect them with relevant information sources and materials modelling solutions, capable
to support optimal materials and process design.
• In this project, I helped in the design and implementation of the infrastructure that manages and stores ontological data and that permits to
query them. Within the project, I used technology such as Docker containers, Stardog triplestore, FastAPIs Python package, GitHub and GitLab.
SimDOME April 2019 ‑ 2022
SimDOME (Digital Ontology‑based Modelling Environment for Simulation of materials) aims to develop an industry‑ready software framework
for materials modelling interoperability, based on EU/ EMMC standards on materials modelling, by combining further developing and adapting
existing software developed within previous EU projects.
• In this project, I helped in the development of a specific use case by building a Python wrapper for a third‑party specific software for chemical
simulations.
