Hi! 👋
My name is Riccardo Massidda, and I'm a third-year ELLIS Ph.D. student at the University of Pisa, Italy, supervised by Davide Bacciu (UniPi) and Sara Magliacane (UvA).
My research lies at the intersection of machine learning and causality and focuses on causal abstraction methods.
Feel free to reach me out at .
📜Publications
Uncertainty in Artificial Intelligence (UAI 2024)
This paper provides theoretical foundations for learning causal abstractions between linear models and introduces Abs-LiNGAM, a method that leverages abstract causal information to execution time of causal discovery of linear non-Gaussian models.
International Conference on Learning Representations (ICLR 2024)
In this paper we introduce COSMO, a constraint-free continuous optimization scheme for acyclic structure learning. In addition to being asymptotically faster, COSMO compares favorably with constrained approaches.
Conference on Causal Learning and Reasoning (CLeaR2023)
Oral Presentation
Causal abstraction provides a theory describing how several causal models can represent the same system at different levels of detail. In this work, we extend existing causal abstraction proposals to soft parametric interventions.
European Conference on Machine Learning (ECML 2022)
Definition of a framework to align ontological concepts and neural directions. Design of ablation experiments to validate the causal role of neurons within semantically coherent clusters.
2020 Evaluation of NLP and Speech Tools for Italian (EVALITA)
Definition of a hierarchical architecture based on sentence-embeddings (USE, LaBSE, SBERT) to solve a document dating task at different granularity levels.
2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)
Development of a data-driven bioinformatic model for the simulation of genomic variants and next-generation sequencing (NGS) reading errors.