no code implementations • 10 Mar 2024 • Ruinan Jin, Wenlong Deng, Minghui Chen, Xiaoxiao Li
UDE is capable of mitigating bias both within the FM API embedding and the images themselves.
no code implementations • 22 Feb 2024 • Wenlong Deng, Blair Chen, Xiaoxiao Li, Christos Thrampoulidis
We achieve fairness while maintaining utility trade-off by ensuring conditional independence between sensitive attributes and text embeddings conditioned on the content.
1 code implementation • 27 Oct 2023 • Wenlong Deng, Christos Thrampoulidis, Xiaoxiao Li
Existing Generalized FL (GFL) and Personalized FL (PFL) methods have limitations in balancing performance across both global and local data distributions.
1 code implementation • 24 Jun 2023 • Anushree Bannadabhavi, Soojin Lee, Wenlong Deng, Xiaoxiao Li
Investigating functional magnetic resonance imaging (fMRI)-based brain functional connectome can aid in the understanding and diagnosis of ASD, leading to more effective treatments.
no code implementations • 6 Jun 2023 • Beidi Zhao, Wenlong Deng, Zi Han, Li, Chen Zhou, Zuhua Gao, Gang Wang, Xiaoxiao Li
We provide appropriate supervision by using slide-level labels to improve the learning of patch-level features.
2 code implementations • 4 Jan 2023 • Wenlong Deng, Yuan Zhong, Qi Dou, Xiaoxiao Li
In this paper, we propose a novel method for fair representation learning with respect to multi-sensitive attributes.
no code implementations • 9 Oct 2022 • Wenlong Deng, Lang Lang, Zhen Liu, Bin Liu
In light of the smoothness property brought by skip connections in ResNet, this paper proposed the Skip Logit to introduce the skip connection mechanism that fits arbitrary DNN dimensions and embraces similar properties to ResNet.