Loading [MathJax]/extensions/MathMenu.js
Liangli Zhen - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Liangli Zhen

Publications
23
Citations
772
Publications by Year
20172025
Co-Authors:
Show All Co-Authors (60)
Image of author Liangli Zhen

Liangli Zhen

Affiliation

Institute of High Performance Computing
Agency for Science Technology and Research (A*STAR)
Connexis North Tower, Singapore

Publication Topics

Biography

Liangli Zhen received the Ph.D. degree in computer science from Sichuan University, Chengdu, China, in 2018.,He is a Senior Scientist and the Group Manager with the Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore. His current research interests include machine learning and multiobjective optimization.(Based on document published on 11 January 2024).
Publications
23
Citations
772
Publications by Year
20172025
Co-Authors:
Show All Co-Authors (60)
Author's Published Works

Showing 1-23 of 23 results

  • Sort

Filter Results

Show

Sort By

Results

Generative Image Reconstruction From Gradients

Ekanut Sotthiwat;Liangli Zhen;Chi Zhang;Zengxiang Li;Rick Siow Mong Goh

IEEE Transactions on Neural Networks and Learning Systems
Year: 2025 | Volume: 36, Issue: 1 | Journal Article |
Cited by: Papers (1)
In this article, we propose a method, generative image reconstruction from gradients (GIRG), for recovering training images from gradients in a federated learning (FL) setting, where privacy is preserved by sharing model weights and gradients rather than raw training data. Previous studies have shown the potential for revealing clients’ private information or even pixel-level recovery of training ...Show More

Generative Image Reconstruction From Gradients

Ekanut Sotthiwat;Liangli Zhen;Chi Zhang;Zengxiang Li;Rick Siow Mong Goh

Year: 2025 | Volume: 36, Issue: 1 | Journal Article |

Category-Aware Test-Time Training Domain Adaptation

Yangqin Feng;Xinxing Xu;Huazhu Fu;Yan Wang;Zizhou Wang;Liangli Zhen;Rick Siow Mong Goh;Yong Liu

2024 IEEE Conference on Artificial Intelligence (CAI)
Year: 2024 | Conference Paper |
Machine learning models often struggle to generalise to out-of-distribution (OOD) data. One promising solution for solving this problem is test-time training domain adaptation, which adjusts a trained model to the new test data without revisiting the source dataset, thus preserving the privacy of source data. However, existing test-time training methods have not considered the mining of category i...Show More

Category-Aware Test-Time Training Domain Adaptation

Yangqin Feng;Xinxing Xu;Huazhu Fu;Yan Wang;Zizhou Wang;Liangli Zhen;Rick Siow Mong Goh;Yong Liu

Year: 2024 | Conference Paper |

Cost-Sensitive Distribution Alignment for Improving Automated Medical Diagnosis Using Retinal Fundus Photography

Yangqin Feng;Xinxing Xu;Zizhou Wang;Yan Wang;Huazhu Fu;Shaohua Li;Liangli Zhen;Tien-En Tan;Mukharram M. Bikbov;Jost B. Jonas;Chee Wai Wong;Ching-Yu Cheng;Daniel Shu Wei Ting;Rick Siow Mong Goh;Yong Liu

2024 IEEE Conference on Artificial Intelligence (CAI)
Year: 2024 | Conference Paper |
Domain adaptation (DA) has emerged as a promising approach to address the domain shift problem in deep learning for automated medical diagnosis. However, current approaches often overlook the imbalanced nature of different categories and primarily focus on aligning the distributions of the source and target domains globally. This oversight leads to suboptimal performance on imbalanced target datas...Show More

Cost-Sensitive Distribution Alignment for Improving Automated Medical Diagnosis Using Retinal Fundus Photography

Yangqin Feng;Xinxing Xu;Zizhou Wang;Yan Wang;Huazhu Fu;Shaohua Li;Liangli Zhen;Tien-En Tan;Mukharram M. Bikbov;Jost B. Jonas;Chee Wai Wong;Ching-Yu Cheng;Daniel Shu Wei Ting;Rick Siow Mong Goh;Yong Liu

Year: 2024 | Conference Paper |

Neural Architecture Search With Progressive Evaluation and Sub-Population Preservation

Yu Xue;Jiajie Zha;Danilo Pelusi;Peng Chen;Tao Luo;Liangli Zhen;Yan Wang;Mohamed Wahib

IEEE Transactions on Evolutionary Computation
Year: 2024 | Early Access Article |
Neural architecture search (NAS) is an effective approach for automating the design of deep neural networks. Evolutionary computation (EC) is commonly used in NAS due to its global optimization capability. However, the evaluation phase of architecture candidates in EC-based NAS is compute-intensive, limiting its application for many real-world problems. To overcome this challenge, we propose a nov...Show More

Neural Architecture Search With Progressive Evaluation and Sub-Population Preservation

Yu Xue;Jiajie Zha;Danilo Pelusi;Peng Chen;Tao Luo;Liangli Zhen;Yan Wang;Mohamed Wahib

Year: 2024 | Early Access Article |

Geometric Correspondence-Based Multimodal Learning for Ophthalmic Image Analysis

Yan Wang;Liangli Zhen;Tien-En Tan;Huazhu Fu;Yangqin Feng;Zizhou Wang;Xinxing Xu;Rick Siow Mong Goh;Yipin Ng;Claire Calhoun;Gavin Siew Wei Tan;Jennifer K. Sun;Yong Liu;Daniel Shu Wei Ting

IEEE Transactions on Medical Imaging
Year: 2024 | Volume: 43, Issue: 5 | Journal Article |
Cited by: Papers (2)
Color fundus photography (CFP) and Optical coherence tomography (OCT) images are two of the most widely used modalities in the clinical diagnosis and management of retinal diseases. Despite the widespread use of multimodal imaging in clinical practice, few methods for automated diagnosis of eye diseases utilize correlated and complementary information from multiple modalities effectively. This pap...Show More

Geometric Correspondence-Based Multimodal Learning for Ophthalmic Image Analysis

Yan Wang;Liangli Zhen;Tien-En Tan;Huazhu Fu;Yangqin Feng;Zizhou Wang;Xinxing Xu;Rick Siow Mong Goh;Yipin Ng;Claire Calhoun;Gavin Siew Wei Tan;Jennifer K. Sun;Yong Liu;Daniel Shu Wei Ting

Year: 2024 | Volume: 43, Issue: 5 | Journal Article |

MedNAS: Multiscale Training-Free Neural Architecture Search for Medical Image Analysis

Yan Wang;Liangli Zhen;Jianwei Zhang;Miqing Li;Lei Zhang;Zizhou Wang;Yangqin Feng;Yu Xue;Xiao Wang;Zheng Chen;Tao Luo;Rick Siow Mong Goh;Yong Liu

IEEE Transactions on Evolutionary Computation
Year: 2024 | Volume: 28, Issue: 3 | Journal Article |
Cited by: Papers (4)
Deep neural networks have demonstrated impressive results in medical image analysis, but designing suitable architectures for each specific task is expertise dependent and time consuming. Neural architecture search (NAS) offers an effective means of discovering architectures. It has been highly successful in numerous applications, particularly in natural image classification. Yet, medical images p...Show More

MedNAS: Multiscale Training-Free Neural Architecture Search for Medical Image Analysis

Yan Wang;Liangli Zhen;Jianwei Zhang;Miqing Li;Lei Zhang;Zizhou Wang;Yangqin Feng;Yu Xue;Xiao Wang;Zheng Chen;Tao Luo;Rick Siow Mong Goh;Yong Liu

Year: 2024 | Volume: 28, Issue: 3 | Journal Article |

Deep Supervised Multi-View Learning With Graph Priors

Peng Hu;Liangli Zhen;Xi Peng;Hongyuan Zhu;Jie Lin;Xu Wang;Dezhong Peng

IEEE Transactions on Image Processing
Year: 2024 | Volume: 33 | Journal Article |
Cited by: Papers (4)
This paper presents a novel method for supervised multi-view representation learning, which projects multiple views into a latent common space while preserving the discrimination and intrinsic structure of each view. Specifically, an apriori discriminant similarity graph is first constructed based on labels and pairwise relationships of multi-view inputs. Then, view-specific networks progressively...Show More

Deep Supervised Multi-View Learning With Graph Priors

Peng Hu;Liangli Zhen;Xi Peng;Hongyuan Zhu;Jie Lin;Xu Wang;Dezhong Peng

Year: 2024 | Volume: 33 | Journal Article |

Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing

Yu Xue;Weinan Tong;Ferrante Neri;Peng Chen;Tao Luo;Liangli Zhen;Xiao Wang

IEEE Transactions on Evolutionary Computation
Year: 2024 | Volume: 28, Issue: 3 | Journal Article |
Cited by: Papers (3)
Generative adversarial networks (GANs) are a powerful generative technique but frequently face challenges with training stability. Network architecture plays a significant role in determining the final output of GANs, but designing a fine architecture demands extensive domain expertise. This article aims to address this issue by searching for high-performance generator’s architectures through neur...Show More

Evolutionary Architecture Search for Generative Adversarial Networks Based on Weight Sharing

Yu Xue;Weinan Tong;Ferrante Neri;Peng Chen;Tao Luo;Liangli Zhen;Xiao Wang

Year: 2024 | Volume: 28, Issue: 3 | Journal Article |

Augmented Multi-Party Computation Against Gradient Leakage in Federated Learning

Chi Zhang;Sotthiwat Ekanut;Liangli Zhen;Zengxiang Li

IEEE Transactions on Big Data
Year: 2024 | Volume: 10, Issue: 6 | Journal Article |
Cited by: Papers (22)
Multi-Party Computation (MPC) provides an effective cryptographic solution for distributed computing systems so that local models with sensitive information are encrypted before sending to the centralized servers for aggregation. Though direct local knowledge leakages are eliminated in MPC-based algorithms, we observe the server can still obtain the local information indirectly in many scenarios, ...Show More

Augmented Multi-Party Computation Against Gradient Leakage in Federated Learning

Chi Zhang;Sotthiwat Ekanut;Liangli Zhen;Zengxiang Li

Year: 2024 | Volume: 10, Issue: 6 | Journal Article |

Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning

Chi Zhang;Xiaoman Zhang;Ekanut Sotthiwat;Yanyu Xu;Ping Liu;Liangli Zhen;Yong Liu

2023 IEEE/CVF International Conference on Computer Vision (ICCV)
Year: 2023 | Conference Paper |
Cited by: Papers (4)
Federated learning has gained recognitions as a secure approach for safeguarding local private data in collaborative learning. But the advent of gradient inversion research has posed significant challenges to this premise by enabling a third-party to recover groundtruth images via gradients. While prior research has predominantly focused on low-resolution images and small batch sizes, this study h...Show More

Generative Gradient Inversion via Over-Parameterized Networks in Federated Learning

Chi Zhang;Xiaoman Zhang;Ekanut Sotthiwat;Yanyu Xu;Ping Liu;Liangli Zhen;Yong Liu

Year: 2023 | Conference Paper |

Deep Semisupervised Multiview Learning With Increasing Views

Peng Hu;Xi Peng;Hongyuan Zhu;Liangli Zhen;Jie Lin;Huaibai Yan;Dezhong Peng

IEEE Transactions on Cybernetics
Year: 2022 | Volume: 52, Issue: 12 | Journal Article |
Cited by: Papers (11)
In this article, we study two challenging problems in semisupervised cross-view learning. On the one hand, most existing methods assume that the samples in all views have a pairwise relationship, that is, it is necessary to capture or establish the correspondence of different views at the sample level. Such an assumption is easily isolated even in the semisupervised setting wherein only a few samp...Show More

Deep Semisupervised Multiview Learning With Increasing Views

Peng Hu;Xi Peng;Hongyuan Zhu;Liangli Zhen;Jie Lin;Huaibai Yan;Dezhong Peng

Year: 2022 | Volume: 52, Issue: 12 | Journal Article |

Deep Supervised Domain Adaptation for Pneumonia Diagnosis From Chest X-Ray Images

Yangqin Feng;Xinxing Xu;Yan Wang;Xiaofeng Lei;Soo Kng Teo;Jordan Zheng Ting Sim;Yonghan Ting;Liangli Zhen;Joey Tianyi Zhou;Yong Liu;Cher Heng Tan

IEEE Journal of Biomedical and Health Informatics
Year: 2022 | Volume: 26, Issue: 3 | Journal Article |
Cited by: Papers (31)
Pneumonia is one of the most common treatable causes of death, and early diagnosis allows for early intervention. Automated diagnosis of pneumonia can therefore improve outcomes. However, it is challenging to develop high-performance deep learning models due to the lack of well-annotated data for training. This paper proposes a novel method, called Deep Supervised Domain Adaptation (DSDA), to auto...Show More

Deep Supervised Domain Adaptation for Pneumonia Diagnosis From Chest X-Ray Images

Yangqin Feng;Xinxing Xu;Yan Wang;Xiaofeng Lei;Soo Kng Teo;Jordan Zheng Ting Sim;Yonghan Ting;Liangli Zhen;Joey Tianyi Zhou;Yong Liu;Cher Heng Tan

Year: 2022 | Volume: 26, Issue: 3 | Journal Article |

Natural Language Video Localization: A Revisit in Span-Based Question Answering Framework

Hao Zhang;Aixin Sun;Wei Jing;Liangli Zhen;Joey Tianyi Zhou;Rick Siow Mong Goh

IEEE Transactions on Pattern Analysis and Machine Intelligence
Year: 2022 | Volume: 44, Issue: 8 | Journal Article |
Cited by: Papers (38)
Natural Language Video Localization (NLVL) aims to locate a target moment from an untrimmed video that semantically corresponds to a text query. Existing approaches mainly solve the NLVL problem from the perspective of computer vision by formulating it as ranking, anchor, or regression tasks. These methods suffer from large performance degradation when localizing on long videos. In this work, we a...Show More

Natural Language Video Localization: A Revisit in Span-Based Question Answering Framework

Hao Zhang;Aixin Sun;Wei Jing;Liangli Zhen;Joey Tianyi Zhou;Rick Siow Mong Goh

Year: 2022 | Volume: 44, Issue: 8 | Journal Article |

Deep Multimodal Transfer Learning for Cross-Modal Retrieval

Liangli Zhen;Peng Hu;Xi Peng;Rick Siow Mong Goh;Joey Tianyi Zhou

IEEE Transactions on Neural Networks and Learning Systems
Year: 2022 | Volume: 33, Issue: 2 | Journal Article |
Cited by: Papers (51)
Cross-modal retrieval (CMR) enables flexible retrieval experience across different modalities (e.g., texts versus images), which maximally benefits us from the abundance of multimedia data. Existing deep CMR approaches commonly require a large amount of labeled data for training to achieve high performance. However, it is time-consuming and expensive to annotate the multimedia data manually. Thus,...Show More

Deep Multimodal Transfer Learning for Cross-Modal Retrieval

Liangli Zhen;Peng Hu;Xi Peng;Rick Siow Mong Goh;Joey Tianyi Zhou

Year: 2022 | Volume: 33, Issue: 2 | Journal Article |

Distributed Monitoring for Energy Infrastructures: A Two-Tier Analysis over Wireless Networks

Chi Zhang;Liangli Zhen;Joey Zhou;Cen Chen

IEEE Wireless Communications
Year: 2021 | Volume: 28, Issue: 6 | Magazine Article |
Cited by: Papers (1)
Wireless networks (e.g., 5G networks) enable distributed energy infrastructures to be connected even when they are geometrically isolated. Intelligent monitoring from remote sites therefore becomes possible, allowing decision makers to examine the status of distributed energy infrastructures from a central location. The major challenge is when local devices cannot perform the monitoring independen...Show More

Distributed Monitoring for Energy Infrastructures: A Two-Tier Analysis over Wireless Networks

Chi Zhang;Liangli Zhen;Joey Zhou;Cen Chen

Year: 2021 | Volume: 28, Issue: 6 | Magazine Article |

Learning Cross-Modal Retrieval with Noisy Labels

Peng Hu;Xi Peng;Hongyuan Zhu;Liangli Zhen;Jie Lin

2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2021 | Conference Paper |
Cited by: Papers (61)
Recently, cross-modal retrieval is emerging with the help of deep multimodal learning. However, even for unimodal data, collecting large-scale well-annotated data is expensive and time-consuming, and not to mention the additional challenges from multiple modalities. Although crowd-sourcing annotation, e.g., Amazon’s Mechanical Turk, can be utilized to mitigate the labeling cost, but leading to the...Show More

Learning Cross-Modal Retrieval with Noisy Labels

Peng Hu;Xi Peng;Hongyuan Zhu;Liangli Zhen;Jie Lin

Year: 2021 | Conference Paper |

Partially Encrypted Multi-Party Computation for Federated Learning

Ekanut Sotthiwat;Liangli Zhen;Zengxiang Li;Chi Zhang

2021 IEEE/ACM 21st International Symposium on Cluster, Cloud and Internet Computing (CCGrid)
Year: 2021 | Conference Paper |
Cited by: Papers (26)
Multi-party computation (MPC) allows distributed machine learning to be performed in a privacy-preserving manner so that end-hosts are unaware of the true models on the clients. However, the standard MPC algorithm also triggers additional communication and computation costs, due to those expensive cryptography operations and protocols. In this paper, instead of applying heavy MPC over the entire l...Show More

Partially Encrypted Multi-Party Computation for Federated Learning

Ekanut Sotthiwat;Liangli Zhen;Zengxiang Li;Chi Zhang

Year: 2021 | Conference Paper |

Evolutionary Multi-Objective Model Compression for Deep Neural Networks

Zhehui Wang;Tao Luo;Miqing Li;Joey Tianyi Zhou;Rick Siow Mong Goh;Liangli Zhen

IEEE Computational Intelligence Magazine
Year: 2021 | Volume: 16, Issue: 3 | Magazine Article |
Cited by: Papers (15)
While deep neural networks (DNNs) deliver state-of-the-art accuracy on various applications from face recognition to language translation, it comes at the cost of high computational and space complexity, hindering their deployment on edge devices. To enable efficient processing of DNNs in inference, a novel approach, called Evolutionary Multi-Objective Model Compression (EMOMC), is proposed to opt...Show More

Evolutionary Multi-Objective Model Compression for Deep Neural Networks

Zhehui Wang;Tao Luo;Miqing Li;Joey Tianyi Zhou;Rick Siow Mong Goh;Liangli Zhen

Year: 2021 | Volume: 16, Issue: 3 | Magazine Article |

Joint Versus Independent Multiview Hashing for Cross-View Retrieval

Peng Hu;Xi Peng;Hongyuan Zhu;Jie Lin;Liangli Zhen;Dezhong Peng

IEEE Transactions on Cybernetics
Year: 2021 | Volume: 51, Issue: 10 | Journal Article |
Cited by: Papers (18)
Thanks to the low storage cost and high query speed, cross-view hashing (CVH) has been successfully used for similarity search in multimedia retrieval. However, most existing CVH methods use all views to learn a common Hamming space, thus making it difficult to handle the data with increasing views or a large number of views. To overcome these difficulties, we propose a decoupled CVH network (DCHN...Show More

Joint Versus Independent Multiview Hashing for Cross-View Retrieval

Peng Hu;Xi Peng;Hongyuan Zhu;Jie Lin;Liangli Zhen;Dezhong Peng

Year: 2021 | Volume: 51, Issue: 10 | Journal Article |

Deep Supervised Cross-Modal Retrieval

Liangli Zhen;Peng Hu;Xu Wang;Dezhong Peng

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year: 2019 | Conference Paper |
Cited by: Papers (305)
Cross-modal retrieval aims to enable flexible retrieval across different modalities. The core of cross-modal retrieval is how to measure the content similarity between different types of data. In this paper, we present a novel cross-modal retrieval method, called Deep Supervised Cross-modal Retrieval (DSCMR). It aims to find a common representation space, in which the samples from different modali...Show More

Deep Supervised Cross-Modal Retrieval

Liangli Zhen;Peng Hu;Xu Wang;Dezhong Peng

Year: 2019 | Conference Paper |

Underdetermined Blind Separation by Combining Sparsity and Independence of Sources

Peng Chen;Dezhong Peng;Liangli Zhen;Yifan Luo;Yong Xiang

IEEE Access
Year: 2017 | Volume: 5 | Journal Article |
Cited by: Papers (11)
In this paper, we address underdetermined blind separation of N sources from their M instantaneous mixtures, where N > M, by combining the sparsity and independence of sources. First, we propose an effective scheme to search some sample segments with the local sparsity, which means that in these sample segments, only Q(Q <; M) sources are active. By grouping these sample segments into different se...Show More

Underdetermined Blind Separation by Combining Sparsity and Independence of Sources

Peng Chen;Dezhong Peng;Liangli Zhen;Yifan Luo;Yong Xiang

Year: 2017 | Volume: 5 | Journal Article |

How to Read Many-Objective Solution Sets in Parallel Coordinates [Educational Forum]

Miqing Li;Liangli Zhen;Xin Yao

IEEE Computational Intelligence Magazine
Year: 2017 | Volume: 12, Issue: 4 | Magazine Article |
Cited by: Papers (85)
Rapid development of evolutionary algor ithms in handling many-objective optimization problems requires viable methods of visualizing a high-dimensional solution set. The parallel coordinates plot which scales well to high-dimensional data is such a method, and has been frequently used in evolutionary many-objective optimization. However, the parallel coordinates plot is not as straightforward as ...Show More

How to Read Many-Objective Solution Sets in Parallel Coordinates [Educational Forum]

Miqing Li;Liangli Zhen;Xin Yao

Year: 2017 | Volume: 12, Issue: 4 | Magazine Article |

Underdetermined Blind Source Separation Using Sparse Coding

Liangli Zhen;Dezhong Peng;Zhang Yi;Yong Xiang;Peng Chen

IEEE Transactions on Neural Networks and Learning Systems
Year: 2017 | Volume: 28, Issue: 12 | Journal Article |
Cited by: Papers (79)
In an underdetermined mixture system with n unknown sources, it is a challenging task to separate these sources from their m observed mixture signals, where m . n. By exploiting the technique of sparse coding, we propose an effective approach to discover some 1-D subspaces from the set consisting of all the time-frequency (TF) representation vectors of observed mixture signals. We show that these ...Show More

Underdetermined Blind Source Separation Using Sparse Coding

Liangli Zhen;Dezhong Peng;Zhang Yi;Yong Xiang;Peng Chen

Year: 2017 | Volume: 28, Issue: 12 | Journal Article |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.