检索结果-内蒙古大学图书馆

A Vertical Federated Multiview Fuzzy Clustering Method for Incomplete Data

学校读者我要写书评

暂无评论

IEEE Transactions on Fuzzy Systems 2025年第5期33卷 1510-1524页

作者： Li, Yan Hu, Xingchen Yu, Shengju Ding, Weiping Pedrycz, Witold Kiat, Yeo Chai Liu, Zhong National University of Defense Technology Laboratory for Big Data and Decision Changsha410073 China National University of Defense Technology School of Computer Changsha410073 China Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China Gliwice44-100 Poland University of Alberta Department of Electrical and Computer Engineering EdmontonABT6G 2R3 Canada Istinye University Research Center of Performance and Productivity Analysis Istanbul34010 Turkey Nanyang Technological University College of Computing and Data Science 639798 Singapore

Multiview fuzzy clustering (MVFC) has gained widespread adoption owing to its inherent flexibility in handling ambiguous data. The proliferation of privatization devices has driven the emergence of new challenge in MVFC research works. Federated learning, a technique that can jointly train without directly using raw data, has gain significant attention in decentralized MVFC. However, their applicability depends on the assumptions of data integrity and independence between different views. In fact, while within distributed environments, data typically exhibits two challenging problems: 1) multiple views within a single client;2) incomplete data. Existing methods exhibit limitations in effectively addressing these challenges. Hence, in this study, we aim at achieving the effective clustering for incomplete data by a novel vertical federated MVFC framework. Specifically, a unified clustering framework is designed to capture both local client learning and global server training. For the local client learning, the data reconstruction strategy and prototype alignment strategy are introduced to ensure the preservation of data structure and refinement of clustering relationships, which mitigates the impact of incomplete data. Meanwhile, the global training process implements aggregation based on client-specific information. The whole process is realized based on the unified fuzzy clustering framework, promoting collaborative learning between client-specific and server information. Theoretical analyses and extensive experiments are carefully conducted to validate the effectiveness and efficiency of the proposed method from multiple perspectives. © 1993-2012 IEEE.

关键词： Data integrity

Unknown-Aware Bilateral Dependency Optimization for Defending Against Model Inversion Attacks

学校读者我要写书评

暂无评论

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 PP页

作者： Peng, Xiong Liu, Feng Wang, Nannan Lan, Long Liu, Tongliang Cheung, Yiu-Ming Han, Bo Hong Kong Baptist University Department of Computer Science Hong Kong The University of Melbourne School of Computing and Information Systems Australia Xidian University State Key Laboratory of Integrated Services Networks School of Telecommunications Engineering Shaanxi Xi'an710071 China National University of Defense Technology State Key Laboratory of High Performance Computing School of Computer Hunan Changsha410000 China The University of Sydney Sydney AI Centre School of Computer Science Faculty of Engineering Australia

By abusing access to a well-trained classifier, model inversion (MI) attacks pose a significant threat as they can recover the original training data, leading to privacy leakage. Previous studies mitigated MI attacks by imposing regularization to reduce the dependency between input features and outputs during classifier training, a strategy known as unilateral dependency optimization. However, this strategy contradicts the objective of minimizing the supervised classification loss, which inherently seeks to maximize the dependency between input features and outputs. Consequently, there is a trade-off between improving the model's robustness against MI attacks and maintaining its classification performance. To address this issue, we propose the bilateral dependency optimization strategy (BiDO), a dual-objective approach that minimizes the dependency between input features and latent representations, while simultaneously maximizing the dependency between latent representations and labels. BiDO is remarkable for its privacy-preserving capabilities. However, models trained with BiDO exhibit diminished capabilities in out-of-distribution (OOD) detection compared to models trained with standard classification supervision. Given the open-world nature of deep learning systems, this limitation could lead to significant security risks, as encountering OOD inputs—whose label spaces do not overlap with the in-distribution (ID) data used during training-is inevitable. To address this, we leverage readily available auxiliary OOD data to enhance the OOD detection performance of models trained with BiDO. This leads to the introduction of an upgraded framework, unknown-aware BiDO (BiDO+), which mitigates both privacy and security concerns. As a highlight, with comparable model utility, BiDO-HSIC+ reduces the FPR95 by 55.02% and enhances the AUCROC by 9.52% compared to BiDO-HSIC, while also providing superior MI robustness. © 1979-2012 IEEE.

关键词： Differential privacy

Numerical simulations of attachment-line boundary layer in hypersonic flow. Part 1. Roughness-induced subcritical transitions

学校读者我要写书评

暂无评论

Journal of Fluid Mechanics 2025年 1009卷

作者： Xi, Youcheng Yan, Bowen Yang, Guangwen Sha, Xinguo Zhu, Dehua Fu, Song School of Aerospace Engineering Tsinghua University Beijing100084 China Institute of High Performance Computing Department of Computer Science and Technology Tsinghua University Beijing100084 China China Academy of Aerospace Aerodynamics Beijing100074 China

The attachment-line boundary layer is critical in hypersonic flows because of its significant impact on heat transfer and aerodynamic performance. In this study, high-fidelity numerical simulations are conducted to analyse the subcritical roughness-induced laminar–turbulent transition at the leading-edge attachment-line boundary layer of a blunt swept body under hypersonic conditions. This simulation represents a significant advancement by successfully reproducing the complete leading-edge contamination process induced by a surface roughness element in a realistic configuration, thereby providing previously unattainable insights. Two roughness elements of different heights are examined. For the lower-height roughness element, additional unsteady perturbations are required to trigger a transition in the wake, suggesting that the flow field around the roughness element acts as a perturbation amplifier for upstream perturbations. Conversely, a higher roughness element can independently induce the transition. A low-frequency absolute instability is detected behind the roughness, leading to the formation of streaks. The secondary instabilities of these streaks are identified as the direct cause of the final transition. © The Author(s), 2025.

关键词： Hypersonic flow

Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for Federated Continual Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Qi, Xiaoming Zhang, Jingyang Fu, Huazhu Yang, Guanyu Li, Shuo Jin, Yueming Department of Biomedical Engineering Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Ministry of Education Nanjing China Institute of High Performance Computing A*STAR Singapore Departments Biomedical Engineering and Computer and Data Science Case Western Reserve University Cleveland United States

Federated continual learning (FCL) offers an emerging pattern to facilitate the applicability of federated learning (FL) in real-world scenarios, where tasks evolve dynamically and asynchronously across clients, especially in medical scenario. Existing server-side FCL methods in nature domain construct a continually learnable server model by client aggregation on all-involved tasks. However, they are challenged by: (1) Catastrophic forgetting for previously learned tasks, leading to error accumulation in server model, making it difficult to sustain comprehensive knowledge across all tasks. (2) Biased optimization due to asynchronous tasks handled across different clients, leading to the collision of optimization targets of different clients at the same time steps. In this work, we take the first step to propose a novel server-side FCL pattern in medical domain, Dynamic Allocation Hypernetwork with adaptive model recalibration (FedDAH). It is to facilitate collaborative learning under the distinct and dynamic task streams across clients. To alleviate the catastrophic forgetting, we propose a dynamic allocation hypernetwork (DAHyper) where a continually updated hypernetwork is designed to manage the mapping between task identities and their associated model parameters, enabling the dynamic allocation of the model across clients. For the biased optimization, we introduce a novel adaptive model recalibration (AMR) to incorporate the candidate changes of historical models into current server updates, and assign weights to identical tasks across different time steps based on the similarity for continual optimization. Extensive experiments on the AMOS dataset demonstrate the superiority of our FedDAH to other FCL methods on sites with different task streams. The code is available:https://***/jinlab-imvr/FedDAH. © 2025, CC BY-SA.

关键词： Federated learning

Dynamic Allocation Hypernetwork with Adaptive Model Recalibration for Federated Continual Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Qi, Xiaoming Zhang, Jingyang Fu, Huazhu Yang, Guanyu Li, Shuo Jin, Yueming Department of Biomedical Engineering Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Ministry of Education Nanjing China Institute of High Performance Computing A*STAR Singapore Departments Biomedical Engineering Computer and Data Science Case Western Reserve University Cleveland United States

关键词： Federated learning

Robust and digital hyper-polarization protocol of nuclear spins via magic sequential sequence

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Haiyang Liao, Hao Wang, Ping Faculty of Arts and Sciences Beijing Normal University Zhuhai519087 China National Engineering Laboratory on Big Data System Computing Technology Guangdong Province Engineering Center of China-made High Performance Data Computing System College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China

Hyper-polarization of nuclear spins is crucial for advancing nuclear magnetic resonance (NMR) and quantum information technologies, as nuclear spins typically exhibit extremely low polarization at room temperature due to their small gyro-magnetic ratios. A promising approach to achieving high nuclear spin polarization is transferring the polarization of electron to nuclear spin. The nitrogen-vacancy (NV) center in diamond has emerged as a highly effective medium for this purpose, and various hyper-polarization protocols have been developed. Among these, the pulsed polarization (PulsePol) method has been extensively studied due to its robustness against static energy shifts of the electron spin. In this study, we introduce a sequential polarization protocol and identify a series of magic and digital sequences for hyper-polarizing nuclear spins. Notably, we demonstrate that some of these magic sequences exhibit significantly greater robustness compared to the PulsePol protocol in the presence of finite half π pulse duration of the protocol. This enhanced robustness positions our protocol as a more suitable candidate for hyper-polarizing nuclear spins species with large gyromagnetic ratios and also ensures better compatibility with high-efficiency readout techniques at high magnetic fields. Additionally, the generality of our protocol allows for its direct application to other solid-state quantum systems beyond the NV center. © 2025, CC BY.

关键词： Chemical shift

Feature Fusion-Guided Network With Sparse Prior Constraints for Unsupervised Hyperspectral Image Quality Improvement

学校读者我要写书评

暂无评论

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Yuan, Feiwang Chen, Yong He, Wei Zeng, Jinshan Jiangxi Normal University School of Computer and Information Engineering Nanchang330022 China Jiangxi Normal University School of Computer and Information Engineering Jiangxi Provincial Key Laboratory for High Performance Computing Nanchang330022 China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan430072 China Xi’an Jiaotong University School of Management Xi’an710049 China

Due to imaging hardware limitations and atmospheric interference, hyperspectral image (HSI) often suffers from low spatial resolution or mixed noise degradation. HSI fusion and denoising are two key strategies to improve HSI quality. Traditional model-based methods rely on data-specific manual priors, while supervised deep learning methods are typically developed specifically for a single task and require a large number of training datasets. To address these limitations, we propose a novel unsupervised feature fusion-guided network (UFFGNet) as a general prior that effectively leverages multiscale semantic features from a guidance image while incorporating sparse prior constraints to suppress outliers. Specifically, UFFGNet comprises a deep feature extraction (DFE) network to capture multiscale semantic features from a guidance image and an attention-based feature generation (AFG) network that generates an output image from random noise. These two networks are connected by a feature refinement module (FRM) to embed the refined features from the feature aggregation module (FAM) into the generation network. Furthermore, the sparse prior constraint is incorporated to model sparse noise (including impulse noise, stripe artifacts, and deadlines) in HSI, thereby improving the robustness of UFFGNet. The proposed network optimizes network parameters in an unsupervised manner without external additional training data, using the fidelity term in the degradation model as a loss function to learn the prior information of the original image. Extensive experiments demonstrate that the proposed UFFGNet outperforms state-of-the-art methods in both HSI fusion and denoising tasks, significantly improving HSI quality. © 1980-2012 IEEE.

关键词： Hyperspectral imaging

APP: Enabling Soft Real-Time Execution on Densely-Populated Hybrid Memory System 23

学校读者我要写书评

暂无评论

APP: Enabling Soft Real-Time Execution on Densely-Populated ...

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Zheng-Wei Wu Yun-Chih Chen Yuan-Hao Chang Tei-Wei Kuo Department of Computer Science and Information Engineering National Taiwan University Institute of Information Science Academia Sinica Taiwan Department of Computer Science and Information Engineering National Taiwan University and Mohamed bin Zayed University of Artificial Intelligence Department of Computer Science and NTU High Performance and Scientific Computing Center National Taiwan University

ISBN: (纸本)9798350323481

Memory swapping was considered slow and evil, but swapping to Ultra Low-Latency storage like Optane has become a promising solution to save power and cost, helping densely-populated edge server to overcome its DRAM capacity bottleneck. However, the lack of integration between CPU scheduling and memory paging causes soft real-time tasks running on edge servers to miss deadlines under heavy memory multiplexing. We propose APP (Adaptive Page Pinning), lightweight protection of working set memory to ensure meeting soft real-time task deadlines without starving other non-real-time tasks. Experiments show that APP alleviates thrashing in memory-intensive tasks and upholds soft real-time task deadlines.

关键词：

Reducing Communication Overhead in Federated Learning for Network Anomaly Detection with Adaptive Client Selection

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Marfo, William Tosh, Deepak K. Moore, Shirley V. Suetterlein, Joshua Manzano, Joseph Department of Computer Science United States High-Performance Computing Group United States University of Texas at El Paso El PasoTX79968 United States Pacific Northwest National Laboratory RichlandWA99354 United States

Communication overhead in federated learning (FL) poses a significant challenge for network anomaly detection systems, where the myriad of client configurations and network conditions can severely impact system efficiency and detection accuracy. While existing approaches attempt to address this through individual optimization techniques, they often fail to maintain the delicate balance between reduced overhead and detection performance. This paper presents an adaptive FL framework that dynamically combines batch size optimization, client selection, and asynchronous updates to achieve efficient anomaly detection. Through extensive profiling and experimental analysis on two distinct datasets—UNSW-NB15 for general network traffic and ROAD for automotive networks—our framework reduces communication overhead by 97.6% (from 700.0s to 16.8s) compared to synchronous baseline approaches while maintaining comparable detection accuracy (95.10% vs. 95.12%). Statistical validation using Mann-Whitney U test confirms significant improvements (p © 2025, CC BY.

关键词： Network security