Research activity

Francesco’s research falls into the broad areas of artificial intelligence and data science, with special emphasis on algorithmic aspects, i.e., on formulating, theoretically characterizing, and designing effective yet efficient algorithms for (novel) problems that are useful to gain insights/information/knowledge from data. As far as data types, special emphasis has been given to graphs, text, and temporal data, but he has also dealt with tabular data, probabilistic data, and semistructured data. Large-scale data processing and combinatorial optimization are frequently-occurring keywords in his work.

More specifically, his recent research interests include:

• Graph machine learning
  • graph representation learning (a.k.a. graph embedding); graph neural networks; machine/graph learning for combinatorial optimization; deep/reinforcement learning paradigms for graph clustering; graph classification;
• Graph data management
  • dense-subgraph discovery; graph summarization; reachability/distance queries on graphs; graph pattern mining; graph clustering; querying graph databases; link prediction;
• Natural Language Processing (NLP)
  • large language models; natural language generation; question answering; word embeddings; text classification; information extraction from text; sentiment analysis/transfer; text summarization; entity recognition and disambiguation;
• Ethics and trustworthiness in data management and AI (algorithmic fairness, explainable AI, interpretability, transparency, privacy, responsible AI, sustainable AI)
• AI in finance

Other topics/problems he has focused on in the past include (social) Web mining (e.g., discovering polarized communities, social-network analysis, information propagation in online services, community search/detection, social-influence analysis, personalization of online services), mining high-dimensional and multifaceted data (i.e., projective/subspace clustering, clustering ensembles, projective clustering ensembles), uncertainty in data mining & machine learning, time-series data management, bioinformatics, XML data management.