Algorithmic Fairness Datasets: Supporting Principled Data Practices

Algorithmic Fairness Datasets:

Supporting Principled Data Practices

HOST: Alessandro Fabris (Università di Padova)

DISCUSSANT: Gian Antonio Susto (Università di Padova)


Lunedì 7 novembre 2022, ore 10.30

Politecnico di Torino, DAUIN - Dipartimento di Automatica e Informatica,
Corso Castelfidardo, 34/A, Torino


Experimental results are only as good as their input data. In machine learning there is a growing awareness that dataset documentation is key to improve data utilization. Much of this awareness comes from the algorithmic fairness community, through a variety of dedicated frameworks and initiatives. This begs the question as to whether this scholarly field has benefitted from its own initiatives and attention to data documentation.

In this talk, I answer in the negative, by describing the current state of data utilization in algorithmic fairness and highlighting some limitations which hinder reliable progress. To address them, I present a tool enabling more principled dataset practices, supporting dataset search from multiple angles, sustained by a wide and standardized documentation effort. Finally, I present the wider relevance and envisioned applications of this initiative for the research community.


Alessandro FABRIS is a PhD candidate at the University of Padua, where he studies algorithmic fairness in information access systems. His research focuses on the definition, operationalization, and measurement of fairness, with a focus on mathematical formalization of domain-specific requirements and a critical perspective on datasets and data ethics.

Gian Antonio SUSTO is currently an Associate Professor with the University of Padova. He earned his Ph.D. from University of Padova and he held visiting positions at University of California at San Diego, Maynooth University and Infineon Technologies Austria AG. He is co-founder of Statwolf LtD. His current research interests include machine and deep learning, industry 4.0 and natural language processing.

Recommended reading:

A. Fabris, S. Messina, G. Silvello, G. Susto, Algorithmic fairness datasets: the story so far, SpringerLink, Open Access, September 17, 2022. LINK