I am a PhD student in the Software and Computer Systems (SCS) department at KTH. I am a Marie-Curie fellow, working on the Marie-Curie ITN project RAIS. My research is currently focused on decentralised machine learning techniques and graph representation learning.
After graduating from Liceo Scientifico G. Galilei, a scientific high school in Verona (Italy), I obtained my bachelor in Computer Science from the University of Trento (Italy) with a thesis on new techniques for LALR parsing. I was then admitted to the EIT Digital Master School, a European double-degree master program, in the Cloud Computing and Services track, with a specialization in Data-Intensive Applications. This allowed me to spend the first year of my master at TU Berlin and then move to KTH Stockholm to complete my education. I graduated in June 2019 with a thesis on gossip-based decentralized machine learning.
While my current research focuses on decentralized machine learning and graph representation learning, I have a broad range of interests, from distributed systems to programming language design and implementation, to cloud computing, data mining and cryptography. I enjoy exploring new topics and bringing together knowledge from different areas to build something new.
My PhD, titled "Machine Learning on Decentralized Networks", focuses on the intersection of decentralized machine learning techniques and graph representation learning, with the final goal of combining techniques from both fields to achieve high-quality insights from a decentralized network. On the decentralized machine learning side, my focus is on Gossip Learning, a scalable, privacy-preserving approach that has not been extensively tested yet. On the graph representation learning side, my focus is currently on the unsupervised modelling of communities, roles, and their inter-dependency. My main supervisor is professor Sarunas Girdijauskas.
The RAIS Project
I am one of 14 PhDs, spread across 6 different organizations, working on the Real-Time Analytics for the Internet of Sports (RAIS) project. The project is part of the Marie-Curie Innovative Training Network (ITN) and is entirely funded by the European Union as part of the Horizon 2020 program. Supported by a network of over a dozen companies, universities and research institutions, we work to tackle the challenges and exploit the opportunities generated by the spread of Internet of Sports (IoS) devices, such as smart bands and smartwatches. RAIS is a strongly international project, with fellows from all over the world studying in 4 different European countries. RAIS is also an interdisciplinary project, approaching the IoS domain from different angles, ranging from human activity recognition to malware detection, decentralized learning and privacy preservation.
I am currently part of three collaborative efforts:
- a RAIS subproject to build a privacy-preserving, decentralized marketplace for ML applications, in collaboration with Ioannis Savvidis from University of Cyprus and Thomas Marchioro from the FORTH research institute, Greece;
- a RAIS collaboration to apply advanced graph representation learning techniques for the detection and containment of malware spreading in large IoT deployments, in collaboration with Ahmed Lekssays from University of Insubria, Italy;
- a cooperation between KTH and the RISE research centre to study the applicability and limitations of data-private NLP training, in collaboration with Abdul Aziz Alkathiri, Daniel Garcia Bernal, Magnus Sahlgren and Sarunas Girdzijauskas.
Master Theses Supervised
- Abdul Aziz Alkathiri, Decentralized Large-Scale Natural Language Processing Using Gossip Learning, 2020
- Daniel Garcia Bernal, Decentralizing Large-Scale Natural Language Processing with Federated Learning, 2020