Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Bai, Ruqi"'
In high-stake domains such as healthcare and hiring, the role of machine learning (ML) in decision-making raises significant fairness concerns. This work focuses on Counterfactual Fairness (CF), which posits that an ML model's outcome on any individu
Externí odkaz:
http://arxiv.org/abs/2409.01977
While prior domain generalization (DG) benchmarks consider train-test dataset heterogeneity, we evaluate Federated DG which introduces federated learning (FL) specific challenges. Additionally, we explore domain-based heterogeneity in clients' local
Externí odkaz:
http://arxiv.org/abs/2307.04942
Answering counterfactual queries has important applications such as explainability, robustness, and fairness but is challenging when the causal variables are unobserved and the observations are non-linear mixtures of these latent variables, such as p
Externí odkaz:
http://arxiv.org/abs/2306.11281
Adversarial examples (AEs) are images that can mislead deep neural network (DNN) classifiers via introducing slight perturbations into original images. This security vulnerability has led to vast research in recent years because it can introduce real
Externí odkaz:
http://arxiv.org/abs/2012.13111
Learning latent causal models from data has many important applications such as robustness, model extrapolation, and counterfactuals. Most prior theoretic work has focused on full causal discovery (i.e., recovering the true latent variables) but requ
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::bf103a827b28d678c0be79faf0438efa
http://arxiv.org/abs/2306.11281
http://arxiv.org/abs/2306.11281
Autor:
Bai, Ruqing
Le travail de thèse porte sur de nouveaux compléments et améliorations pour la théorie de la péridynamique concernant la modélisation numérique de structures minces telles que les poutres et les plaques, les composites isotropes et multicouche
Externí odkaz:
http://www.theses.fr/2019COMP2482