Junyuan Hong
Overview
Explore the profile of Junyuan Hong including associated specialties, affiliations and a list of published articles.
Author names and details appear as published. Due to indexing inconsistencies, multiple individuals may share a name, and a single author may have variations. MedLuna displays this data as publicly available, without modification or verification
Snapshot
Snapshot
Articles
11
Citations
27
Followers
0
Related Specialties
Related Specialties
Top 10 Co-Authors
Top 10 Co-Authors
Published In
Published In
Affiliations
Affiliations
Soon will be listed here.
Recent Articles
1.
Deng Y, Hong J, Zhou J, Mahdavi M
Proc Mach Learn Res
. 2024 Oct;
238:4519-4527.
PMID: 39420981
Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. However, a rigorous understanding of how the representation function learned on an unlabeled...
2.
Zhang H, Hong J, Deng Y, Mahdavi M, Zhou J
Adv Neural Inf Process Syst
. 2024 Apr;
36:3921-3944.
PMID: 38606303
Deep Gradient Leakage (DGL) is a highly effective attack that recovers private training images from gradient vectors. This attack casts significant privacy challenges on distributed learning from clients with sensitive...
3.
Federated Robustness Propagation: Sharing Adversarial Robustness in Heterogeneous Federated Learning
Hong J, Wang H, Wang Z, Zhou J
Proc AAAI Conf Artif Intell
. 2023 Oct;
37(7):7893-7901.
PMID: 37846298
Federated learning (FL) emerges as a popular distributed learning schema that learns a model from a set of participating users without sharing raw data. One major challenge of FL comes...
4.
Hong J, Lyu L, Zhou J, Spranger M
Adv Neural Inf Process Syst
. 2023 May;
35:20133-20146.
PMID: 37151570
As deep learning blooms with growing demand for computation and data resources, outsourcing model training to a powerful cloud server becomes an attractive alternative to training at a low-power and...
5.
Hong J, Wang Z, Zhou J
FACCT 2022 (2022)
. 2023 Apr;
2022:11-35.
PMID: 37084074
Protecting privacy in learning while maintaining the model performance has become increasingly critical in many applications that involve sensitive data. Private Gradient Descent (PGD) is a commonly used private learning...
6.
Wang H, Hong J, Zhang A, Zhou J, Wang Z
Adv Neural Inf Process Syst
. 2023 Apr;
35:36026-36039.
PMID: 37081923
Deep neural networks (DNNs) are vulnerable to backdoor attacks. Previous works have shown it extremely challenging to unlearn the undesired backdoor behavior from the network, since the entire network can...
7.
Wang H, Hong J, Zhou J, Wang Z
Transact Mach Learn Res
. 2023 Apr;
2023.
PMID: 37056515
Increasing concerns have been raised on deep learning fairness in recent years. Existing fairness-aware machine learning methods mainly focus on the fairness of in-distribution data. However, in real-world applications, it...
8.
Zhu Z, Hong J, Drew S, Zhou J
Proc Mach Learn Res
. 2023 Apr;
162:27504-27526.
PMID: 37056291
The rise of Federated Learning (FL) is bringing machine learning to edge computing by utilizing data scattered across edge devices. However, the heterogeneity of edge network topologies and the uncertainty...
9.
Hong J, Zhu Z, Yu S, Wang Z, Dodge H, Zhou J
KDD
. 2022 May;
2021:617-627.
PMID: 35571559
Federated learning is a distributed learning framework that is communication efficient and provides protection over participating users' raw training data. One outstanding challenge of federate learning comes from the users'...
10.
Zhu Z, Hong J, Zhou J
Proc Mach Learn Res
. 2022 Apr;
139:12878-12889.
PMID: 35480385
Federated Learning (FL) is a decentralized machine-learning paradigm in which a global server iteratively aggregates the model parameters of local users without accessing their data. User has imposed significant challenges...