Hi, I'm Paolo Morettin!

[...]

What I do

[ GitHub, Twitter, LinkedIn]

Person

Probabilistic {reasoning, learning} with {logical, algebraic} constraints

Currently: Assistant professor (RTD-A) @ DISI, University of Trento, Italy.

Previously: Postdoc researcher @ DTAI, KU Leuven, Belgium.

News

Mar 2023: New job & MSCA fellowship

Happy to announce that I have joined back the ranks of University of Trento as an assistant professor (RTD-A, for those who are familiar with the Italian system). Plus, I was awarded with a Marie Skłodowska-Curie Action fellowship! My project will start on March 2024, focusing on applications of my work to the formal verification of AI systems.

Feb 2023: Top reviewer @ AISTATS 2023

I was selected as a top reviewer at AISTATS 2023. Full list here.

Aug 2022: Joining the MLJ editorial board

I was invited to join the editorial board of the Machine Learning Journal. Happy to help with the reviewing process!

Jul 2022: Tutorial @ IJCAI 2022

I'm co-organizing a tutorial on probabilistic inference with algebraic and logical constraints with Pedro Zuidberg Dos Martires, Samuel Kolb and Andrea Passerini at the 31st International Joint Conference on Artificial Intelligence. More information here. Looking forward to meeting you in Vienna!

Apr 2022: My PhD Thesis became a book!

My PhD thesis got recently published by IOS Press in the book series "Frontiers in Artificial Intelligence and Applications". You can find it here.

Recent publications

[Full list at: Google Scholar DBLP ]

2022

[UAI] SMT-based Weighted Model Integration with Structure Awareness
Giuseppe Spallitta, Gabriele Masina, Paolo Morettin, Andrea Passerini, Roberto Sebastiani

2021

[IJCAI] Hybrid Probabilistic Inference with Logical and Algebraic Constraints: a Survey
Paolo Morettin, Pedro Zuidberg Dos Martires, Samuel Kolb, Andrea Passerini

2020

[NeurIPS] Probabilistic Inference with Algebraic Constraints: Theoretical Limits and Practical Approximations
Zhe Zeng, Paolo Morettin, Fanqi Yan, Antonio Vergari, Guy Van den Broeck

[NeurIPS] Efficient Generation of Structured Objects with Constrained Adversarial Networks
Luca Di Liello, Pierfrancesco Ardino, Jacopo Gobbi, Paolo Morettin, Stefano Teso, Andrea Passerini

[ICML] Scaling up Hybrid Probabilistic Inference with Logical and Arithmetic Constraints via Message Passing
Zhe Zeng, Paolo Morettin, Fanqi Yan, Antonio Vergari, Guy Van den Broeck

[AAAI] Learning Weighted Model Integration distributions
Paolo Morettin, Samuel Kolb, Stefano Teso, Andrea Passerini

2019

[IJCAI] The pywmi Framework and Toolbox for Probabilistic Inference using WMI
Samuel Kolb, Paolo Morettin, Pedro Zuidberg Dos Martires, Francesco Sommavilla, Andrea Passerini, Roberto Sebastiani, Luc De Raedt

[AIJ] Advanced SMT techniques for Weighted Model Integration
Paolo Morettin, Andrea Passerini, Roberto Sebastiani

2017

[IJCAI] Efficient Weighted Model Integration via SMT-Based Predicate Abstraction
Paolo Morettin, Andrea Passerini, Roberto Sebastiani

Software

[ReCoIn] RElax, COmpensate, INtegrate: an approximate Weighted Model Integration approach for pairwise models.

[MP-WMI] Tractable Weighted Model Integration via message passing

[LARIAT] Learning Weighted Model Integration distributions

[pywmi] A python toolbox for probabilistic modelling and inference using Weighted Model Integration

[WMI-PA] A general SMT-based WMI solver for exact probabilistic inference

Service

Teaching:

TA, Fundamentals of AI (2023) - Material
TA, Uncertainty in AI (2021, 2022)
TA, CS for BSc in Biotechnologies (2018-2019)

Program/reviewing committee member:

AAAI 2021 2022 2023 2024
AISTATS 2022 2023 2024
ECAI 2020
ICLR 2022 2023 2024
ICML 2021 2022 2023
IJCAI 2020 2021 2022 2023
NeurIPS 2020 2021 2022

Reviewer for journals:

Machine Learning Journal (editorial board member)
Journal of Machine Learning Research
Frontiers in AI
Data Mining and Knowledge Discovery
Künstliche Intelligenz (Journal of AI of the German Informatics Society)