← Search

Benin Godfrey L

2 accepted papers

2024

Towards Learning and Explaining Indirect Causal Effects in Neural Networks

AAAI 2024technical

Recently, there has been a growing interest in learning and explaining causal effects within Neural Network (NN) models. By virtue of NN architectures, previous approaches consider only direct and total causal effects assuming independence among input variables. We view an NN as a structural causal…

2022

On Causally Disentangled Representations

AAAI 2022technical

Representation learners that disentangle factors of variation have already proven to be important in addressing various real world concerns such as fairness and interpretability. Initially consisting of unsupervised models with independence assumptions, more recently, weak supervision and correlated…