Zobrazeno 1 - 10
of 707
pro vyhledávání: '"A., Kagal"'
Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for marginalized communi
Externí odkaz:
http://arxiv.org/abs/2412.01711
Publikováno v:
Transactions on Graph Data and Knowledge, Vol 2, Iss 2, Pp 1:1-1:2 (2024)
In this Special Issue of Transactions on Graph Data and Knowledge - entitled "Resources for Graph Data and Knowledge" - we present eight articles that describe key resources in the area. These resources cover a wide range of topics within the scope o
Externí odkaz:
https://doaj.org/article/58a1646e4a8141198465e8525141889c
Autor:
Bauer, Nicholas J.C., Alfawaz, Abdullah F., Kha, Lan-Chau, Kagal, Eliana S., Bowers, Nicolas G.R., Singh, Sheldon M.
Publikováno v:
In CJC Open December 2024 6(12):1521-1526
Publikováno v:
CJC Open, Vol 6, Iss 3, Pp 556-559 (2024)
Information is evolving on the safety of same-day discharge (SDD) after left atrial appendage occlusion (LAAO) procedures. This single-centre retrospective study evaluated the feasibility of SDD and reported on the 30-day rehospitalization rate in pa
Externí odkaz:
https://doaj.org/article/9e4ad2e6489540b1897b858300c54ffe
Vertical Federated Learning (VFL) refers to the collaborative training of a model on a dataset where the features of the dataset are split among multiple data owners, while label information is owned by a single data owner. In this paper, we propose
Externí odkaz:
http://arxiv.org/abs/2106.05468
Federated Generative Adversarial Network (FedGAN) is a communication-efficient approach to train a GAN across distributed clients without clients having to share their sensitive training data. In this paper, we experimentally show that FedGAN generat
Externí odkaz:
http://arxiv.org/abs/2103.09876
Autor:
Tong, Schrasing, Kagal, Lalana
We evaluated whether model explanations could efficiently detect bias in image classification by highlighting discriminating features, thereby removing the reliance on sensitive attributes for fairness calculations. To this end, we formulated importa
Externí odkaz:
http://arxiv.org/abs/2012.05463
Generative Adversarial Networks (GANs) are deep learning architectures capable of generating synthetic datasets. Despite producing high-quality synthetic images, the default GAN has no control over the kinds of images it generates. The Information Ma
Externí odkaz:
http://arxiv.org/abs/2010.11398
Federated learning enables the development of a machine learning model among collaborating agents without requiring them to share their underlying data. However, malicious agents who train on random data, or worse, on datasets with the result classes
Externí odkaz:
http://arxiv.org/abs/2007.03856
Federated learning is a technique that enables distributed clients to collaboratively learn a shared machine learning model while keeping their training data localized. This reduces data privacy risks, however, privacy concerns still exist since it i
Externí odkaz:
http://arxiv.org/abs/2002.08423