Decentralized Data Mining & Information Network Analytics
Royal Institute of Technology (KTH), Sweden
Prof. Šarūnas Girdzijauskas
Graph Representation Learning, Decentralized Machine Learning, Machine Learning over Networks
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.
I am now continuing on that line of research with a PhD on decentralized data mining and machine learning, part of the RAIS project, funded by the EU Marie-Curie Innovative Training Network.
While my current research focuses on decentralized machine 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 and unique.
The world we live in can be often described in terms of networks: social networks, computer networks, networks of Internet of Things or Internet of Sports devices. Understanding the phenomena underlying these networks is fundamental in order to advance our society. My work within the RAIS project focuses on two key issues related to this topic.
The first issue is how to use Machine Learning to understand the structure of complex networks and predict their evolution. The second issue is how to safely and effectively perform Machine Learning tasks on top of an existing network of devices, in a decentralized fashion, exploiting the computational power of all these devices, while still maintaining their data private. The final goal of my research is to be able to combine the solutions of these two issues, known as Graph Representation Learning and Decentralized Privacy-Preserving Machine Learning, in a way that can be directly applied to a variety of tasks.
As an example application, consider an Internet of Sports sensor/app that can record the user activity and his/her interactions with other users. With these technologies, it would be possible for the app to analyze the behaviour of the user and provide exercise recommendations, without sharing any raw information with any central entity, thus providing the best user experience without compromising privacy.
L. Giaretta, ‘Pushing the Limits of Gossip-Based Decentralised Machine Learning’, Master Thesis, 2019, http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-253794