Zobrazeno 1 - 10
of 184
pro vyhledávání: '"Hu, Hongsheng"'
Autor:
Zhu, Zhiyu, Jin, Zhibo, Hu, Hongsheng, Xue, Minhui, Sun, Ruoxi, Camtepe, Seyit, Gauravaram, Praveen, Chen, Huaming
AI systems, in particular with deep learning techniques, have demonstrated superior performance for various real-world applications. Given the need for tailored optimization in specific scenarios, as well as the concerns related to the exploits of su
Externí odkaz:
http://arxiv.org/abs/2411.06146
With the growing applications of Deep Learning (DL), especially recent spectacular achievements of Large Language Models (LLMs) such as ChatGPT and LLaMA, the commercial significance of these remarkable models has soared. However, acquiring well-trai
Externí odkaz:
http://arxiv.org/abs/2411.05051
For any crystallographic root system, let $W$ be the associated Weyl group, and let $\mathit{WP}$ be the weight polytope (also known as the $W$-permutohedron) associated with an arbitrary strongly dominant weight. The action of $W$ on $\mathit{WP}$ i
Externí odkaz:
http://arxiv.org/abs/2410.13617
Autor:
Ma, Binhao, Zheng, Tianhang, Hu, Hongsheng, Wang, Di, Wang, Shuo, Ba, Zhongjie, Qin, Zhan, Ren, Kui
Machine learning models trained on vast amounts of real or synthetic data often achieve outstanding predictive performance across various domains. However, this utility comes with increasing concerns about privacy, as the training data may include se
Externí odkaz:
http://arxiv.org/abs/2407.05112
Autor:
Chi, Xiaoxiao, Zhang, Xuyun, Wang, Yan, Qi, Lianyong, Beheshti, Amin, Xu, Xiaolong, Choo, Kim-Kwang Raymond, Wang, Shuo, Hu, Hongsheng
Recommender systems have been successfully applied in many applications. Nonetheless, recent studies demonstrate that recommender systems are vulnerable to membership inference attacks (MIAs), leading to the leakage of users' membership privacy. Howe
Externí odkaz:
http://arxiv.org/abs/2405.07018
Machine unlearning has become a promising solution for fulfilling the "right to be forgotten", under which individuals can request the deletion of their data from machine learning models. However, existing studies of machine unlearning mainly focus o
Externí odkaz:
http://arxiv.org/abs/2404.03233
Bj\"orner and Ekedahl [Ann. of Math. (2), 170.2(2009), pp. 799--817] pioneered the study of length-counting sequences associated with parabolic lower Bruhat intervals in crystallographic Coxeter groups. In this paper, we study the asymptotic behavior
Externí odkaz:
http://arxiv.org/abs/2311.17980
For any root system of rank $r$, we study the "dominant weight polytope" $P^\lambda$ associated with a strongly dominant weight $\lambda$. We prove that $P^\lambda$ is combinatorially equivalent to the $r$-dimensional cube. As an application, we give
Externí odkaz:
http://arxiv.org/abs/2311.16022
Autor:
Hu, Hongsheng, Zhang, Xuyun, Salcic, Zoran, Sun, Lichao, Choo, Kim-Kwang Raymond, Dobbie, Gillian
Federated learning (FL) is a popular approach to facilitate privacy-aware machine learning since it allows multiple clients to collaboratively train a global model without granting others access to their private data. It is, however, known that FL ca
Externí odkaz:
http://arxiv.org/abs/2310.00222
Autor:
Hu, Hongsheng, Wang, Shuo, Chang, Jiamin, Zhong, Haonan, Sun, Ruoxi, Hao, Shuang, Zhu, Haojin, Xue, Minhui
The right to be forgotten requires the removal or "unlearning" of a user's data from machine learning models. However, in the context of Machine Learning as a Service (MLaaS), retraining a model from scratch to fulfill the unlearning request is impra
Externí odkaz:
http://arxiv.org/abs/2309.08230