Giovanni De Toni
PhD Student, Machine Learning
Mobile and Social Computing Lab, Fondazione Bruno Kessler
Structured Machine Learning Group, University of Trento
European Laboratory for Learning and Intelligent Systems (ELLIS)
I am a PhD student at Fondazione Bruno Kessler (FBK) and European Laboratory for Learning and Intelligent Systems (ELLIS), under the supervision of Bruno Lepri (FBK), Andrea Passerini (University of Trento) and Manuel Gomez Rodriguez (Max Planck Institute for Software Systems). My research interests relate to fair & explainable AI topics, focusing on algorithmic recourse, causality, counterfactual explanations and user-aware decision making systems.
During the PhD, I also interned at X, the moonshot factory (Google X) where I worked on Large Language Models (LLMs) applied to program synthesis supervised by Dr. Rishabh Singh in Mountain View, CA.
Before the PhD, I was a Research Scientist at VUI, Inc., a Boston's startup building innovative conversational agents and a Research Assistant in the Structured Machine Learning Group (SML) at the University of Trento, Italy.
During my undergraduate studies, I interned at CERN (2019), and I spent a semester at the University of Edinburgh (2018) as an Erasmus student. I also participated in the Google Summer of Code (2017) as a Software Developer for Shogun, a machine learning library. I received my Bachelor and Master's degree (cum laude) from the University of Trento in 2017 and 2020 respectively. I also obtained a scholarship for my academic performance through my undergraduate studies.
In my free time, I enjoy climbing, hiking, reading and chess. I also spend a lot of time thinking about how to (safely) automatize human activity with (explainable and fair) intelligent agents.
Latest News
- 01/2024 Personalized Algorithmic Recourse with Preference Elicitation (with P. Viappiani, S. Teso, B. Lepri and A. Passerini) has been accepted on Transactions on Machine Learning Research!
- 10/2023: This fall/winter I will be interning at Max Planck Institute for Software Systems, Kaiserslautern, Germany, under the supervision of Dr. Manuel Gomez Rodriguez working on human-centric machine learning research!
- 09/2023: I presented "Personalized Algorithmic Recourse with Preference Elicitation" at the First Workshop on Hybrid Human-Machine Learning and Decision Making happening at ECML-PKDD 2023 in Turin, Italy!
- 07/2023: Together with Luna Bianchi, we gave a talk titled "Hidden Implications of AI Systems: why we need AI ethics and fairness" talking about algorithmic recourse at the EIT Summer School on IoT and Digital Interactive Smart Spaces held in Milan, Italy.
- 06/2023: Spent a wonderful week at the Nordic Probabilistic AI School learning more on probabilistic modelling, variational inference and Bayesian neural networks!
- 02/2023: "Personalized Algorithmic Recourse with Preference Elicitation" (with P. Viappiani, B. Lepri and A. Passerini) is now available on arxiv!
- 10/2022: Generating personalized counterfactual interventions for algorithmic recourse by eliciting user preferences (with P. Viappiani, B. Lepri and A. Passerini) was accepted at NeurIPS 2022 workshop on Human in the Loop Learning (HILL)!
- 09/2022: I presented "Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis" (with B. Lepri and A. Passerini) as a poster at the 2nd ELLIS Doctoral Symposium in Alicante, Spain
- 05/2022: New preprint released "Generating personalized counterfactual interventions for algorithmic recourse by eliciting user preferences" (with P. Viappiani, B. Lepri and A. Passerini)
- 03/2022: This summer I will be interning at X, the moonshot factory (Google X), Mountain View, CA under the supervision of Dr. Rishabh Singh working on a secret program synthesis project!
- 02/2022: I gave a short presentation on "Algorithmic Recourse and Counterfactual Interventions" during the second session of the SML Journal Club! The slides and the recording are available!
- 01/2022: New preprint released "Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis" (with B. Lepri and A. Passerini)!
- 12/2021: Given an introductory seminar on Program Synthesis as part of the Advanced Topics in Machine Learning and Optimization course for the Master's Degree in Artificial Intelligence Systems at the University of Trento. You can find the slides here!
- 12/2021: Our research on estimating influenza cases in Europe with Wikipedia was featured in an article on the "Berliner Zeitung" (in German)!
- 10/2021: Learning compositional programs with arguments and sampling was accepted at NeurIPS 2021 workshop Advances in Programming Languages and Neurosymbolic Systems !
- 10/2021: Participated in the ELLIS Doctoral Symposium in Tübingen where I presented Learning compositional programs with arguments and sampling as a poster!
- 10/2021: I am officially starting my joint PhD at FBK/University of Trento as part of the ELLIS network!
- 09/2021: Learning compositional programs with arguments and sampling was accepted at the 10th International Workshop on Statistical Relational AI at IJCLR 2021!
Publications & Preprints
- Personalized Algorithmic Recourse with Preference Elicitation
Giovanni De Toni, Paolo Viappiani, Stefano Teso, Bruno Lepri, Andrea Passerini
Transactions on Machine Learning Research (2024)
[paper][code]
A preliminary version of this work was accepted at the at NeurIPS 2022 workshop on Human in the Loop Learning (HILL).
See here for the previous paper.
- Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
Giovanni De Toni, Bruno Lepri, Andrea Passerini
Machine Learning (2023)
[paper][code]
- Learning compositional programs with arguments and sampling
Giovanni De Toni, Luca Erculiani, Andrea Passerini
Advances in Programming Languages and Neurosymbolic Systems (AIPLANS), NeurIPS, 2021.
10th International Workshop on Statistical Relational AI (StarAI), IJCLR, 2021.
[paper][code][poster]
- A general method for estimating the prevalence of Influenza-Like-Symptoms with Wikipedia data
Giovanni De Toni, Cristian Consonni, Alberto Montresor
PLOS ONE, 2021.
[paper][code]
- Pyglmnet: Python implementation of elastic-net regularized generalized linear models
Mainak Jas, Titipat Achakulvisut, Aid Idrizović, Daniel Acuna, Matthew Antalek, Vinicius Marques, Tommy Odland, Ravi Prakash Garg, Mayank Agrawal, Yu Umegaki, Peter Foley, Hugo Fernandes, Drew Harris, Beibin Li, Olivier Pieters, Scott Otterson, Giovanni De Toni, Chris Rodgers, Eva Dyer, Matti Hamalainen, Konrad Kording, Pavan Ramkumar
Journal of Open Source Software (JOSS), 2020.
[paper][code]
Teaching
- Fall 2023: Machine Learning (MSc in Artificial Intelligence Systems)
- Fall 2022: Machine Learning (MSc in Computer Science)
- Fall 2022: Machine Learning (MSc in Artificial Intelligence Systems)
- Fall 2021: Software Programming I
- Fall 2020: Software Programming I