no code implementations • 9 Mar 2024 • Tiejin Chen, Wenwang Huang, Linsey Pang, Dongsheng Luo, Hua Wei
This paper delves into the critical area of deep learning robustness, challenging the conventional belief that classification robustness and explanation robustness in image classification systems are inherently correlated.
no code implementations • 7 Mar 2024 • Tiejin Chen, Longchao Da, Huixue Zhou, Pingzhi Li, Kaixiong Zhou, Tianlong Chen, Hua Wei
The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT.
no code implementations • 11 Jan 2024 • Zicheng Wang, Tiejin Chen, Qinrun Dai, Yueqi Chen, Hua Wei, Qingkai Zeng
Compartmentalization effectively prevents initial corruption from turning into a successful attack.
1 code implementation • 3 Jan 2024 • Kai Ye, Tiejin Chen, Hua Wei, Liang Zhan
The Evidential Regression Network (ERN) represents a novel approach that integrates deep learning with Dempster-Shafer's theory to predict a target and quantify the associated uncertainty.
1 code implementation • 30 Dec 2023 • Longchao Da, Kuanru Liou, Tiejin Chen, Xuesong Zhou, Xiangyong Luo, Yezhou Yang, Hua Wei
Transportation has greatly benefited the cities' development in the modern civilization process.
no code implementations • 22 Dec 2023 • Tiejin Chen, Yuanpu Cao, Yujia Wang, Cho-Jui Hsieh, Jinghui Chen
Specifically, FedPTR allows local clients or the server to optimize an auxiliary (synthetic) dataset that mimics the learning dynamics of the recent model update and utilizes it to project the next-step model trajectory for local training regularization.
no code implementations • 15 Dec 2022 • Tiejin Chen, Yicheng Tao
With the learned value and fixed non-zero positions for sketch matrices from learning-based algorithms, these matrices can reduce the test error of low rank approximation significantly.