Publications
Learning Hybrid Interpretable Models: Theory, Taxonomy, and Methods
A hybrid model involves the cooperation of an interpretable model and a complex black box. At inference, any input of the hybrid model is assigned to either its interpretable or complex component based on a gating mechanism. The ratio of data samples sent to the interpretable component is referred to as the model trans ...
A Survey on Fairness Without Demographics
The issue of bias in Machine Learning (ML) models is a significant challenge for the machine learning community. Real-world biases can be embedded in the data used to train models, and prior studies have shown that ML models can learn and even amplify these biases. This can result in unfair treatment of individuals bas ...
Events
Data anonymization
Both a method for guaranteeing data security for some, and a legal obligation to protect personal information for others, data anonymization is a topical notion federating computer sciences and social sciences. Indeed, the recent adoption of Bill 25 in Quebec and discussio ...