A review of the gumbel-max trick and its extensions for discrete stochasticity in machine learning

IAM Huijben, W Kool, MB Paulus… - IEEE transactions on …, 2022 - ieeexplore.ieee.org
The Gumbel-max trick is a method to draw a sample from a categorical distribution, given by
its unnormalized (log-) probabilities. Over the past years, the machine learning community …

Comparative analysis of membership inference attacks in federated learning

S Dayal, D Alhadidi, A Abbasi Tadi… - Proceedings of the 27th …, 2023 - dl.acm.org
Given a federated learning model and a record, a membership inference attack can
determine whether this record is part of the model's training dataset. Federated learning is a …

Part-and-whole: A novel framework for deformable medical image registration

J Zhang, Z Liu, Y Ma, X Zhao, B Yang - Applied Intelligence, 2023 - Springer
Medical image registration is a vital initial step in medical image analysis that aims to
establish accurate correspondence between image pairs. Various methods have achieved …

On the global self-attention mechanism for graph convolutional networks

C Wang, C Deng - 2020 25th International Conference on …, 2021 - ieeexplore.ieee.org
Applying Global Self-attention (GSA) mechanism over features has achieved remarkable
success on Convolutional Neural Networks (CNNs). However, it is not clear if Graph …

On the robustness and generalization of deep learning driven full waveform inversion

C Deng, Y Lin - arxiv preprint arxiv:2111.14220, 2021 - arxiv.org
The data-driven approach has been demonstrated as a promising technique to solve
complicated scientific problems. Full Waveform Inversion (FWI) is commonly epitomized as …

Une revue systématique de la littérature autour du biais, de l'équité et de l'explicabilité

ML Ndao, G Youness, N Niang… - … Conférence Nationale en …, 2023 - cnam.hal.science
Ce travail fournit une analyse d'une bibliographie autour du biais de l'équité et de
l'explicabilité des algorithmes de l'IA entre 2015 et 2022. Par une approche de Traitement …