431 citations · 727 across the 10 of their papers we have counts for
5 papers · 1 filter
Tsallis Regularized Optimal Transport and Ecological Inference
Boris Muzellec, Richard Nock, Giorgio Patrini +1
Optimal transport is a powerful framework for computing distances between probability distributions. We unify the two main approaches to optimal transport, namely Monge-Kantorovitc…
Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach
Giorgio Patrini, Alessandro Rozza, Aditya Menon +2
We present a theoretically grounded approach to train deep neural networks, including recurrent networks, subject to class-dependent label noise. We propose two procedures for loss…
The Crossover Process: Learnability and Data Protection from Inference Attacks
Richard Nock, Giorgio Patrini, Finnian Lattimore +1
It is usual to consider data protection and learnability as conflicting objectives. This is not always the case: we show how to jointly control inference --- seen as the attack ---…
Fast Learning from Distributed Datasets without Entity Matching
Giorgio Patrini, Richard Nock, Stephen Hardy +1
Consider the following data fusion scenario: two datasets/peers contain the same real-world entities described using partially shared features, e.g. banking and insurance company r…
Loss factorization, weakly supervised learning and label noise robustness
Giorgio Patrini, Frank Nielsen, Richard Nock +1
We prove that the empirical risk of most well-known loss functions factors into a linear term aggregating all labels with a term that is label free, and can further be expressed by…