We live in a world where a terrific amount of data is produced every day. Such an abundance of data led to recent breakthroughs in AI, which are revolutionizing our societies, economies, and everyday lives. As a consequence, data is becoming an extremely valuable asset in all domains, ranging from healthcare and finance to education and entertainment.
Research in AI is striving to build systems based on machine learning techniques that can effectively learn from data. Such systems are usually designed as complex machine learning pipelines that involve several actors with potentially misaligned goals, since they might need to gather information from several independent data sources, acquire data from the outside world, or even outsource learning tasks.
When multiple actors with different goals interact among each other, the strategic component becomes crucial. Surprisingly, this has been largely neglected by AI research.
The STRATDATA project, coordinated by Prof. Alberto Marchesi from the Department of Electronics, Information and Bioengineering at the Politecnico di Milano and funded by the Italian Fund for Science (FIS), aims at developing a principled framework to understand and effectively control the strategic interactions arising in complex machine learning pipelines. The main issue is represented by the fact that strategic actors may behave untruthfully to their advantage, by hiding data or altering machine learning models. The main goal of the project is to provide principled ways in which such untruthful behavior can be prevented, so as to ensure that all the actors involved make a trustworthy use of data and machine learning models.
The project revolves around three core pillars, each one devoted to a different type of strategic interaction. The first one is devoted to information gathering problems, which are ubiquitous in distributed data infrastructures. The second pillar is about information markets where data and machine learning models are traded by AI systems, while the third pillar is concerned with the problem of delegating learning tasks.
Alberto Marchesi is an Assistant Professor at the Department of Electronics, Information, and Bioengineering of Politecnico di Milano, within the Artificial Intelligence and Robotics Lab. His research focuses on algorithmic game theory and machine learning, with the aim of bridging the two fields to build novel AI systems. He got his PhD in Information Technology with laude from Politecnico di Milano. His PhD thesis was awarded the 2020 Chorafas Award by the Dimitris N. Chorafas Foundation and received an honorable mention for the 2020 EurAI Dissertation Award. He is the author of more than 60 peer-reviewed research papers, including papers published in premier journals, such as Journal of the ACM, Artificial Intelligence Journal (8), Algorithmica, and Games and Economic Behavior, and in top-tier international conferences, such as NeurIPS (13), ICML (5), EC (3), SODA, AAAI (7), IJCAI (8), AAMAS (3), ICLR (2), AISTATS (2) and UAI. One of his papers was awarded an "Outstanding Paper Award" at NeurIPS 2020, which is the most important annual gathering in the field of AI and machine learning (only 3 papers have been selected out of 9467 submissions).
He serves as Areac Chair for several top-tier conferences in AI and machine learning, and he was also guest associate editor for the Frontiers in Artificial Intelligence journal. He was involved in several research and industrial projects, taking the role of principal investigator (PI) in some of them. Currently, he is co-PI of a PRIN 2022 project funded by the MUR, co-PI of a research unit in the "ELIAS" project funded by HORIZON-RIA, and co-leader of a workpackage of the Spoke 4 in the "PNRR-PE FAIR - Future Artificial Intelligence Research" project, funded by NextGenerationEU. In 2020, he co-founded ML cube s.r.l., which is a startup part of the spin-off program of Politecnico di Milano. He also taught several courses at BSc, MSc and PhD level on computer science and AI.