publications

2022

1. Fair Interpretable Representation Learning with Correction Vectors

   Mattia Cerrato, Alesia Vallenas Coronel, Marius Köppel, and 3 more authors

   CoRR, 2022

2021

1. Fair Interpretable Learning via Correction Vectors

   Mattia Cerrato, Marius Köppel, Alexander Segner, and 1 more author

   In Workshops of the Ninth International Conference on Learning Representations (ICLR 2021), 2021
2. Fair Group-Shared Representations with Normalizing Flows

   Mattia Cerrato, Marius Köppel, Alexander Segner, and 1 more author

   In Workshops of the Ninth International Conference on Learning Representations (ICLR 2021), 2021
3. Ranking Algorithms for Word Ordering in Surface Realization

   Alessandro Mazzei, Mattia Cerrato, Roberto Esposito, and 1 more author

   Information, 2021

2020

1. Fair pairwise learning to rank

   Mattia Cerrato, Marius Köppel, Alexander Segner, and 2 more authors

   In Proceedings of the 6th IEEE Conference on Data Science and Advanced Analytics, 2020
2. Constraining Deep Representations with a Noise Module for Fair Classification

   Mattia Cerrato, Roberto Esposito, and Laura Li Puma

   In Proceedings of the 35th Annual ACM Symposium on Applied Computing, 2020

   Abs

   The recent surge in interest for Deep Learning (motivated by its exceptional performances on longstanding problems) made Neural Networks a very appealing tool for many actors in our society. One issue in this shift of interest is that Neural Networks are very opaque objects and it is often hard to make sense of their predictions.In this context, research efforts have focused on building fair representations of data which display little to no correlation with regard to a sensitive attribute s. In this paper we build onto a domain adaptation neural model by augmenting it with a "noise conditioning" mechanism which we show is instrumental in obtaining fair (i.e. non-correlated with s) representations. We provide experiments on standard datasets showing the effectiveness of the noise conditioning mechanism in helping the networks to ignore the sensible attribute.

2019

1. Partitioned Least Squares

   Roberto Esposito, Mattia Cerrato, and Marco Locatelli

   In AI*IA 2019 – Advances in Artificial Intelligence, 2019
2. Taxonomic and Whole Object Constraints: A Deep Architecture

   Mattia Cerrato, Edoardo Arnaudo, Valentina Gliozzi, and 1 more author

   In Cognitive Science, 2019

2018