Hi! 👋

My name is Riccardo Massidda, and I'm a third-year Ph.D. student at the University of Pisa.

My research lies at the intersection of machine learning, neural network interpretability, and causality.

Feel free to reach me out at name.surname (at) phd.unipi.it.

Photo of Riccardo Massidda

📜Publications

Constraint-Free Structure Learning with Smooth Acyclic Orientations

Riccardo Massidda, Francesco Landolfi, Martina Cinquini, Davide Bacciu

arXiv (Preprint)

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.

Causal Abstraction with Soft Interventions

Riccardo Massidda, Atticus Geiger, Thomas Icard, Davide Bacciu

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.

Knowledge-Drive Interpretation of Convolutional Neural Networks

Riccardo Massidda, Davide Bacciu

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.

rmassidda@ DaDoEval: Document Dating Using Sentence Embeddings at EVALITA 2020

Riccardo Massidda

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.

Technology and Species independent Simulation of Sequencing data and Genomic Variants

Filippo Geraci, Riccardo Massidda, Nadia Pisanti

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.