no code implementations • 6 Sep 2023 • Keyu Chen, Di Zhuang, Mingchen Li, J. Morris Chang
Experiments on English-German and English-Romanian translation show that: (i) Epi-Curriculum improves both model's robustness and adaptability in seen and unseen domains; (ii) Our episodic training framework enhances the encoder and decoder's robustness to domain shift.
no code implementations • 1 Feb 2023 • G. Dumindu Samaraweera, Hung Nguyen, Hadi Zanddizari, Behnam Zeinali, J. Morris Chang
Recent breakthrough technological progressions of powerful mobile computing resources such as low-cost mobile GPUs along with cutting-edge, open-source software architectures have enabled high-performance deep learning on mobile platforms.
1 code implementation • 28 May 2022 • Mingchen Li, Di Zhuang, J. Morris Chang
MC-GEN applies multi-level clustering and differential private generative model to improve the utility of synthetic data.
no code implementations • 11 Feb 2022 • Keyu Chen, Di Zhuang, J. Morris Chang
The results show that our two-stage training strategy effectively addresses the class imbalance classification problem, and significantly improves existing works in terms of F1-score and AUC score, resulting in state-of-the-art performance.
1 code implementation • 7 Feb 2022 • Di Zhuang, Mingchen Li, J. Morris Chang
As such, it motivates the researchers to conduct distributed deep learning, where the data user would like to build DL models using the data segregated across multiple different data owners.
no code implementations • 6 Jul 2021 • Nam Nguyen, J. Morris Chang
This study proposed a novel framework for COVID-19 severity prediction, which is a combination of data-centric and model-centric approaches.
no code implementations • 20 Jun 2021 • Thee Chanyaswad, J. Morris Chang, S. Y. Kung
Compressive Privacy is a privacy framework that employs utility-preserving lossy-encoding scheme to protect the privacy of the data, while multi-kernel method is a kernel based machine learning regime that explores the idea of using multiple kernels for building better predictors.
1 code implementation • 21 Feb 2021 • Nam Nguyen, J. Morris Chang
This paper proposes a novel cell-based neural architecture search algorithm (NAS), which completely alleviates the expensive costs of data labeling inherited from supervised learning.
no code implementations • 22 Jan 2021 • Hadi Zanddizari, Behnam Zeinali, J. Morris Chang
In this paper, we propose a novel approach to generate a black-box attack in sparse domain whereas the most important information of an image can be observed.
3 code implementations • 1 Nov 2020 • Keyu Chen, Di Zhuang, J. Morris Chang
The generalization capability of machine learning models, which refers to generalizing the knowledge for an "unseen" domain via learning from one or multiple seen domain(s), is of great importance to develop and deploy machine learning applications in the real-world conditions.
Ranked #26 on Domain Generalization on VLCS
no code implementations • 9 May 2020 • Di Zhuang, J. Morris Chang
Later, our approach leverages the learned knowledge to precisely perturb the data owners' data into privatized data that can be successfully utilized for certain intended purpose (learning to succeed), without jeopardizing certain predefined privacy (training to fail).
no code implementations • 25 Apr 2020 • Di Zhuang, Nam Nguyen, Keyu Chen, J. Morris Chang
Hence, most of the mobile healthcare systems leverage the cloud computing infrastructure, where the data collected by the mobile and IoT devices would be transmitted to the cloud computing platforms for analysis.
no code implementations • 25 Apr 2020 • Di Zhuang, Keyu Chen, J. Morris Chang
Since the skin lesion datasets are usually limited and statistically biased, while designing an effective fusion approach, it is important to consider not only the performance of each classifier on the training/validation dataset, but also the relative discriminative power (e. g., confidence) of each classifier regarding an individual sample in the testing phase, which calls for an active fusion approach.
no code implementations • 9 Feb 2020 • Sen Wang, J. Morris Chang
To protect the image privacy, we propose to locally perturb the image representation before revealing to the data user.
no code implementations • 6 Feb 2020 • Sen Wang, J. Morris Chang
The privacy concern raises when such data leaves the hand of the owners and be further explored or mined.
no code implementations • 3 May 2019 • Emre Yilmaz, Mohammad Al-Rubaie, J. Morris Chang
In order to train a Naive Bayes classifier in an untrusted setting, we propose to use methods satisfying local differential privacy.
no code implementations • 27 Mar 2018 • Mohammad Al-Rubaie, J. Morris Chang
For privacy concerns to be addressed adequately in current machine learning systems, the knowledge gap between the machine learning and privacy communities must be bridged.
1 code implementation • 25 Sep 2017 • Di Zhuang, J. Morris Chang, Mingchen Li
Community detection is of great importance for online social network analysis.
Social and Information Networks Cryptography and Security