João Fonseca worked as a Research Intern at NYU during spring 2023,
advised by Professor Julia Stoyanovich and working closely with Andrew Bell
and Venetia Pliatsika, with whom he continues to collaborate. He
completed his Ph.D. and is an Invited Assistant Professor at NOVA
Information Management School (Lisbon, Portugal). João Fonseca’s work aims to answer
open questions on algorithmic recourse, Explainable AI, and Synthetic Data
Generation.
João likes to play guitar, padel tennis, bouldering and surfing.
Selected publications
ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations
@article{explainerPFN,title={ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations},author={Fonseca, Joao and Stoyanovich, Julia},year={2026},eprint={2601.23068},archiveprefix={arXiv},primaryclass={cs.LG},author+an={2=self},keywords={working,explainability,transparency},}
ShaRP: Explaining Rankings and Preferences with Shapley Values
Venetia Pliatsika, João Fonseca, Kateryna Akhynko, Ivan Shevchenko, and Julia Stoyanovich
@article{sharp,author={Pliatsika, Venetia and Fonseca, Jo{\~{a}}o and Akhynko, Kateryna and Shevchenko, Ivan and Stoyanovich, Julia},title={{ShaRP}: Explaining Rankings and Preferences with Shapley Values},journal={Proc. {VLDB} Endow.},volume={18},number={11},year={2025},doi={10.14778/3749646.3749682},keywords={journal,data,ranking,explainability,transparency,RAIforUkraine}}
SHAP-based Explanations are Sensitive to Feature Representation
Hyunseung Hwang, Andrew Bell, Joao Fonseca, Venetia Pliatsika, Julia Stoyanovich, and Steven Euijong Whang
In Conference on Fairness, Accountability, and Transparency, ACM FAccT 2025
@inproceedings{sharp_attack,title={{SHAP}-based Explanations are Sensitive to Feature Representation},author={Hwang, Hyunseung and Bell, Andrew and Fonseca, Joao and Pliatsika, Venetia and Stoyanovich, Julia and Whang, Steven Euijong},year={2025},booktitle={Conference on Fairness, Accountability, and Transparency, {ACM FAccT}},keywords={conference,data,explainability,transparency}}
SafeNudge: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs
Joao Fonseca, Andrew Bell, and Julia Stoyanovich
In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP) Nov 2025
@inproceedings{fonseca-etal-2025-safenudge,title={{SafeNudge}: Safeguarding Large Language Models in Real-time with Tunable Safety-Performance Trade-offs},author={Fonseca, Joao and Bell, Andrew and Stoyanovich, Julia},booktitle={Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)},month=nov,year={2025},publisher={ACM},doi={10.18653/v1/2025.emnlp-main.1010},pages={19955--19969},isbn={979-8-89176-332-6},keywords={conference,privacy,safety}}
Setting the Right Expectations: Algorithmic Recourse Over Time
João Fonseca, Andrew Bell, Carlo Abrate, Francesco Bonchi, and Julia Stoyanovich
In Proceedings of the 3rd ACM Conference on Equity and Access in Algorithms,
Mechanisms, and Optimization, EAAMO 2023, Boston, MA, USA, 30 October
2023 - 1 November 2023 Nov 2023
@inproceedings{DBLP:conf/eaamo/FonsecaBABS23,author={Fonseca, Jo{\~{a}}o and Bell, Andrew and Abrate, Carlo and Bonchi, Francesco and Stoyanovich, Julia},title={Setting the Right Expectations: Algorithmic Recourse Over Time},booktitle={Proceedings of the 3rd {ACM} Conference on Equity and Access in Algorithms,
Mechanisms, and Optimization, {EAAMO} 2023, Boston, MA, USA, 30 October
2023 - 1 November 2023},pages={29:1--29:11},publisher={{ACM}},year={2023},url={https://doi.org/10.1145/3617694.3623251},doi={10.1145/3617694.3623251},timestamp={Thu, 09 Nov 2023 21:12:58 +0100},biburl={https://dblp.org/rec/conf/eaamo/FonsecaBABS23.bib},bibsource={dblp computer science bibliography, https://dblp.org},keywords={conference, fairness}}
How Much Effort Is Enough? Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity
Andrew Bell, Joao Fonseca, Carlo Abrate, Francesco Bonchi, and Julia Stoyanovich
In Equity and Access in Algorithms, Mechanisms, and Optimization, EAAMO Nov 2025
@inproceedings{fairrecourse,title={How Much Effort Is Enough? Fairness in Algorithmic Recourse Through the Lens of Substantive Equality of Opportunity},author={Bell, Andrew and Fonseca, Joao and Abrate, Carlo and Bonchi, Francesco and Stoyanovich, Julia},year={2025},booktitle={Equity and Access in Algorithms, Mechanisms, and Optimization, {EAAMO}},publisher={{ACM}},doi={10.1145/3757887.3763014},keywords={conference,fairness}}
The Game Of Recourse: Simulating Algorithmic Recourse over Time to
Improve Its Reliability and Fairness
Andrew Bell, João Fonseca, and Julia Stoyanovich
In Companion of the 2024 International Conference on Management of Data,
SIGMOD/PODS 2024, Santiago AA, Chile, June 9-15, 2024 Nov 2024
@inproceedings{DBLP:conf/sigmod/BellFS24,author={Bell, Andrew and Fonseca, Jo{\~{a}}o and Stoyanovich, Julia},editor={Barcel{\'{o}}, Pablo and Pi, Nayat S{\'{a}}nchez and Meliou, Alexandra and Sudarshan, S.},title={The Game Of Recourse: Simulating Algorithmic Recourse over Time to
Improve Its Reliability and Fairness},booktitle={Companion of the 2024 International Conference on Management of Data,
{SIGMOD/PODS} 2024, Santiago AA, Chile, June 9-15, 2024},pages={464--467},publisher={{ACM}},year={2024},url={https://doi.org/10.1145/3626246.3654742},doi={10.1145/3626246.3654742},keywords={fairness,conference,demo},author+an={1=self;2=self;3=self},}
