Vito Paolo Pastore — accepted AI-conference papers

2026

Bias In, Bias Out? Finding Unbiased Subnetworks in Vanilla Models

Ivan Luiz De Moura Matos, Abdel Djalil Sad Saoud, Ekaterina Iakovleva, Vito Paolo Pastore, Enzo Tartaglione

CVPR 2026

The issue of algorithmic biases in deep learning has led to the development of various debiasing techniques, many of which perform complex training procedures or dataset manipulation. However, an intriguing question arises: is it possible to extract fair and bias-agnostic subnetworks from standard v

Cited by 0 Source ↗code ↗Scholar ↗

2026

Distribution Alignment for One-Shot Federated Learning via Optimal Transport

Daniele Berardini, Vito Paolo Pastore, Vittorio Murino

ICML 2026poster

One-Shot Federated Learning (OSFL) addresses extreme communication regimes in which clients interact with the server only once, amplifying the impact of heterogeneous client data distributions. In particular, the interaction of domain shift and label shift across clients induces misaligned feature r…

Cited by 0 Source ↗Scholar ↗

2025

Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing

Massimiliano Ciranni, Vito Paolo Pastore, Roberto Di Via, Enzo Tartaglione, Francesca Odone, Vittorio Murino

NeurIPS 2025poster

The effectiveness of deep learning models in classification tasks is often challenged by the quality and quantity of training data whenever they are affected by strong spurious correlations between specific attributes and target labels. This results in a form of bias affecting training data, which t…

Cited by 0 Source ↗code ↗Scholar ↗