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.
1 code implementation • 1 Jan 2024 • Ruinan Jin, Chun-Yin Huang, Chenyu You, Xiaoxiao Li
Notably, MedCLIP, a vision-language contrastive learning-based medical FM, has been designed using unpaired image-text training.
no code implementations • 3 Jun 2023 • Ruinan Jin, Minghui Chen, Qiong Zhang, Xiaoxiao Li
To this end, we propose the Forgettable Federated Linear Learning (2F2L) framework featured with novel training and data removal strategies.
1 code implementation • 4 Mar 2023 • Chun-Yin Huang, Ruinan Jin, Can Zhao, Daguang Xu, Xiaoxiao Li
To address this, we propose a new method, called Federated Virtual Learning on Heterogeneous Data with Local-Global Distillation (FedLGD), which trains FL using a smaller synthetic dataset (referred as virtual data) created through a combination of local and global dataset distillation.
no code implementations • 19 Oct 2022 • Ruinan Jin, Xiaoxiao Li
However, given that the FL server cannot access the raw data, it is vulnerable to backdoor attacks, an adversarial by poisoning training data.
1 code implementation • 2 Jul 2022 • Ruinan Jin, Xiaoxiao Li
In this study, we propose a way of attacking federated GAN (FedGAN) by treating the discriminator with a commonly used data poisoning strategy in backdoor attack classification models.
no code implementations • ICLR 2022 • Ruinan Jin, Yu Xing, Xingkang He
First, we prove that the iterates of mSGD are asymptotically convergent to a connected set of stationary points with probability one, which is more general than existing works on subsequence convergence or convergence of time averages.
no code implementations • 23 Sep 2021 • Difei Cheng, Ruihang Xu, Bo Zhang, Ruinan Jin
Density-based clustering algorithms are widely used for discovering clusters in pattern recognition and machine learning since they can deal with non-hyperspherical clusters and are robustness to handle outliers.
no code implementations • 15 Apr 2021 • Chao Cai, Ruinan Jin, Peng Wang, Liyuan Ye, Hongbo Jiang, Jun Luo
Recently, \textit{passive behavioral biometrics} (e. g., gesture or footstep) have become promising complements to conventional user identification methods (e. g., face or fingerprint) under special situations, yet existing sensing technologies require lengthy measurement traces and cannot identify multiple users at the same time.