Khanh Nguyen
Khanh Nguyen has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Dinh Phung
Monash University, Melbourne, VIC, Australia
3 shared publications - Trung Le
Monash University, Melbourne, VIC, Australia
3 shared publications - Alexander Verl
University of Stuttgart
1 shared publication - Anh Phan Viet
Le Quy Don Technical University
1 shared publication - Cuong Nguyen Manh
Vietnam Academy of Science and Technology, Institute of Physics, Hanoi, Vietnam
1 shared publication - Geoffrey I. Webb
Department of Data Science and Artificial Intelligence, Monash University, Melbourne, Australia
1 shared publication
Latest Publications
- 25 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 218-223
Feature-Space Reinforcement Learning for Robotic Manipulation
Reinforcement Learning (RL) has gained popularity for developing intelligent robots, but challenges such as sample inefficiency and lack of generalization persist. The choice of observation space significantly influences RL algorithms' sample efficiency in robotics. While end-to-end learning has been emphasized, it increases complexity and inefficiency as the agent must re-learn forward and inverse kinematics. To address these issues, we propose a straightforward approach that utilizes readily available control techniques, such as forward and inverse kinematics, to capitalize on domain knowledge. Our approach involves enhancing the observation space with task-space features and utilizing task-space inverse kinematics. Our contributions include a proposal for mathematical formulation and a framework for RL algorithms in robotics.
- 25 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 218-223
Feature-Space Reinforcement Learning for Robotic Manipulation
Reinforcement Learning (RL) has gained popularity for developing intelligent robots, but challenges such as sample inefficiency and lack of generalization persist. The choice of observation space significantly influences RL algorithms' sample efficiency in robotics. While end-to-end learning has been emphasized, it increases complexity and inefficiency as the agent must re-learn forward and inverse kinematics. To address these issues, we propose a straightforward approach that utilizes readily available control techniques, such as forward and inverse kinematics, to capitalize on domain knowledge. Our approach involves enhancing the observation space with task-space features and utilizing task-space inverse kinematics. Our contributions include a proposal for mathematical formulation and a framework for RL algorithms in robotics.
- Open Access
- 7 January 2022
- Published by Springer Nature in Machine Learning
- Vol. 111 (3) , 997-1018
Improving kernel online learning with a snapshot memory
- 7 January 2022
- Published by Springer Nature in Machine Learning
- Vol. 111 (3) , 997-1018
Open AccessImproving kernel online learning with a snapshot memory
- 19 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Linguistic-based Augmentation for Enhancing Vietnamese Sentiment Analysis
Identify customer’s opinions about products, services, and brands bring many benefits to e-commerce development. Capturing customer attitudes helps retailers adjust business decisions. Customers can select the suitable product and the good service by consulting social experiences. However, free-style texts of customer feedback like acronyms, slang words, incorrect grammar, and so on are challenging any machine learning model.
- 19 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Linguistic-based Augmentation for Enhancing Vietnamese Sentiment Analysis
Identify customer’s opinions about products, services, and brands bring many benefits to e-commerce development. Capturing customer attitudes helps retailers adjust business decisions. Customers can select the suitable product and the good service by consulting social experiences. However, free-style texts of customer feedback like acronyms, slang words, incorrect grammar, and so on are challenging any machine learning model.
- 1 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 34 (9) , 4425-4438
Robust Variational Learning for Multiclass Kernel Models With Stein Refinement
Kernel-based models have a strong generalization ability, but most of them, including SVM, are vulnerable to the curse of kernelization. Moreover, their predictive performances are sensitive to the hyperparameters tuning, which highly demands computational resources. These problems render kernel methods problematic when dealing with large-scale datasets. To this end, we first formulate the optimization problem in a kernel-based learning setting as a posterior inference problem, and then develop a rich family of Recurrent Neural Network-based variational inference techniques. Unlike existing literature, which stops at the variational distribution and uses it as the surrogate for the true posterior distribution, here we further leverage Stein Variational Gradient Descent to further bring the variational distribution closer to the true posterior, we refer to this step as Stein Refinement. Putting these altogether, we arrive at a robust and efficient variational learning method for multiclass kernel machines with extremely accurate approximation. Moreover, our formulation enables efficient learning of kernel parameters and hyperparameters which robustifies the proposed method against data uncertainties. The extensive experimental results show that our method, without tuning any parameter, obtains comparable performance to LIBSVM, a well-known implementation of SVM, and outperforms other baselines while being able to seamlessly scale with large-scale datasets.
- 1 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 34 (9) , 4425-4438
Robust Variational Learning for Multiclass Kernel Models With Stein Refinement
Kernel-based models have a strong generalization ability, but most of them, including SVM, are vulnerable to the curse of kernelization. Moreover, their predictive performances are sensitive to the hyperparameters tuning, which highly demands computational resources. These problems render kernel methods problematic when dealing with large-scale datasets. To this end, we first formulate the optimization problem in a kernel-based learning setting as a posterior inference problem, and then develop a rich family of Recurrent Neural Network-based variational inference techniques. Unlike existing literature, which stops at the variational distribution and uses it as the surrogate for the true posterior distribution, here we further leverage Stein Variational Gradient Descent to further bring the variational distribution closer to the true posterior, we refer to this step as Stein Refinement. Putting these altogether, we arrive at a robust and efficient variational learning method for multiclass kernel machines with extremely accurate approximation. Moreover, our formulation enables efficient learning of kernel parameters and hyperparameters which robustifies the proposed method against data uncertainties. The extensive experimental results show that our method, without tuning any parameter, obtains comparable performance to LIBSVM, a well-known implementation of SVM, and outperforms other baselines while being able to seamlessly scale with large-scale datasets.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Deep Domain Adaptation for Vulnerable Code Function Identification
Due to the ubiquity of computer software, software vulnerability detection (SVD) has become crucial in the software industry and in the field of computer security. Two significant issues in SVD arise when using machine learning, namely: i) how to learn automatic features that can help improve the predictive performance of vulnerability detection and ii) how to overcome the scarcity of labeled vulnerabilities in projects that require the laborious labeling of code by software security experts. In this paper, we address these two crucial concerns by proposing a novel architecture which leverages deep domain adaptation with automatic feature learning for software vulnerability identification. Based on this architecture, we keep the principles and reapply the state-of-the-art deep domain adaptation methods to indicate that deep domain adaptation for SVD is plausible and promising. Moreover, we further propose a novel method named Semi-supervised Code Domain Adaptation Network (SCDAN) that can efficiently utilize and exploit information carried in unlabeled target data by considering them as the unlabeled portion in a semi-supervised learning context. The proposed SCDAN method enforces the clustering assumption, which is a key principle in semi-supervised learning. The experimental results using six real-world software project datasets show that our SCDAN method and the baselines using our architecture have better predictive performance by a wide margin compared with the Deep Code Network (VulDeePecker) method without domain adaptation. Also, the proposed SCDAN significantly outperforms the DIRT-T which to the best of our knowledge is currently the-state-of-the-art method in deep domain adaptation and other baselines.
- 1 July 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Deep Domain Adaptation for Vulnerable Code Function Identification
Due to the ubiquity of computer software, software vulnerability detection (SVD) has become crucial in the software industry and in the field of computer security. Two significant issues in SVD arise when using machine learning, namely: i) how to learn automatic features that can help improve the predictive performance of vulnerability detection and ii) how to overcome the scarcity of labeled vulnerabilities in projects that require the laborious labeling of code by software security experts. In this paper, we address these two crucial concerns by proposing a novel architecture which leverages deep domain adaptation with automatic feature learning for software vulnerability identification. Based on this architecture, we keep the principles and reapply the state-of-the-art deep domain adaptation methods to indicate that deep domain adaptation for SVD is plausible and promising. Moreover, we further propose a novel method named Semi-supervised Code Domain Adaptation Network (SCDAN) that can efficiently utilize and exploit information carried in unlabeled target data by considering them as the unlabeled portion in a semi-supervised learning context. The proposed SCDAN method enforces the clustering assumption, which is a key principle in semi-supervised learning. The experimental results using six real-world software project datasets show that our SCDAN method and the baselines using our architecture have better predictive performance by a wide margin compared with the Deep Code Network (VulDeePecker) method without domain adaptation. Also, the proposed SCDAN significantly outperforms the DIRT-T which to the best of our knowledge is currently the-state-of-the-art method in deep domain adaptation and other baselines.
- 18 August 2007
- Published by Springer Nature
- p. 117-150
Hierarchical Architectures for Reasoning