Zobrazeno 1 - 10
of 266
pro vyhledávání: '"Zou, Na"'
Graph Neural Networks (GNNs) have been increasingly deployed in a plethora of applications. However, the graph data used for training may contain sensitive personal information of the involved individuals. Once trained, GNNs typically encode such inf
Externí odkaz:
http://arxiv.org/abs/2407.19398
There has been significant progress in improving the performance of graph neural networks (GNNs) through enhancements in graph data, model architecture design, and training strategies. For fairness in graphs, recent studies achieve fair representatio
Externí odkaz:
http://arxiv.org/abs/2312.12369
In social network, a person located at the periphery region (marginal node) is likely to be treated unfairly when compared with the persons at the center. While existing fairness works on graphs mainly focus on protecting sensitive attributes (e.g.,
Externí odkaz:
http://arxiv.org/abs/2310.14527
In real-world applications, machine learning models often become obsolete due to shifts in the joint distribution arising from underlying temporal trends, a phenomenon known as the "concept drift". Existing works propose model-specific strategies to
Externí odkaz:
http://arxiv.org/abs/2310.01508
Parkinson's disease (PD), a neurodegenerative disorder, often manifests as speech and voice dysfunction. While utilizing voice data for PD detection has great potential in clinical applications, the widely used deep learning models currently have fai
Externí odkaz:
http://arxiv.org/abs/2309.13292
Domain generalization aims to learn a generalization model that can perform well on unseen test domains by only training on limited source domains. However, existing domain generalization approaches often bring in prediction-irrelevant noise or requi
Externí odkaz:
http://arxiv.org/abs/2307.07181
Despite the impressive prediction ability, machine learning models show discrimination towards certain demographics and suffer from unfair prediction behaviors. To alleviate the discrimination, extensive studies focus on eliminating the unequal distr
Externí odkaz:
http://arxiv.org/abs/2307.04105
This paper introduces the Fair Fairness Benchmark (\textsf{FFB}), a benchmarking framework for in-processing group fairness methods. Ensuring fairness in machine learning is important for ethical compliance. However, there exist challenges in compari
Externí odkaz:
http://arxiv.org/abs/2306.09468
We study graph data augmentation by mixup, which has been used successfully on images. A key operation of mixup is to compute a convex combination of a pair of inputs. This operation is straightforward for grid-like data, such as images, but challeng
Externí odkaz:
http://arxiv.org/abs/2306.06788
Autor:
Ding, Sirui, Tan, Qiaoyu, Chang, Chia-yuan, Zou, Na, Zhang, Kai, Hoot, Nathan R., Jiang, Xiaoqian, Hu, Xia
Organ transplant is the essential treatment method for some end-stage diseases, such as liver failure. Analyzing the post-transplant cause of death (CoD) after organ transplant provides a powerful tool for clinical decision making, including personal
Externí odkaz:
http://arxiv.org/abs/2304.00012