检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Jiao, Yang Yang, Kai Wu, Tiancheng Jian, Chengtao Huang, Jianwei Department of Computer Science and Technology Tongji University China Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China Shanghai Research Institute for Intelligent Autonomous Systems China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society China

Trilevel learning, also called trilevel optimization (TLO), has been recognized as a powerful modelling tool for hierarchical decision process and widely applied in many machine learning applications, such as robust neural architecture search, hyperparameter optimization, and domain adaptation. Tackling TLO problems has presented a great challenge due to their nested decision-making structure. In addition, existing works on TLO face the following key challenges: 1) they all focus on the non-distributed setting, which may lead to privacy breach;2) they do not offer any non-asymptotic convergence analysis which characterizes how fast an algorithm converges. To address the aforementioned challenges, this paper proposes an asynchronous federated trilevel optimization method to solve TLO problems. The proposed method utilizes µ-cuts to construct a hyper-polyhedral approximation for the TLO problem and solve it in an asynchronous manner. We demonstrate that the proposed µ-cuts are applicable to not only convex functions but also a wide range of non-convex functions that meet the µ-weakly convex assumption. Furthermore, we theoretically analyze the non-asymptotic convergence rate for the proposed method by showing its iteration complexity to obtain ϵ-stationary point is upper bounded by (Formula Presented). Extensive experiments on real-world datasets have been conducted to elucidate the superiority of the proposed method, e.g., it has a faster convergence rate with a maximum acceleration of approximately 80%. Copyright © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Training for stable explanation for free 24

Training for stable explanation for free

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Chao Chen Chenghua Guo Rufeng Chen Guixiang Ma Ming Zeng Xiangwen Liao Xi Zhang Sihong Xie School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) China Key Laboratory of Trustworthy Distributed Computing and Service (MoE) Beijing University of Posts and Telecommunications China Artificial Intelligence Thrust The Hong Kong University of Science and Technology (Guangzhou) China Intel Carnegie Mellon University College of Computer and Data Science Fuzhou University China

ISBN: (纸本)9798331314385

To foster trust in machine learning models, explanations must be faithful and stable for consistent insights. Existing relevant works rely on the ℓp distance for stability assessment, which diverges from human perception. Besides, existing adversarial training (AT) associated with intensive computations may lead to an arms race. To address these challenges, we introduce a novel metric to assess the stability of top-k salient features. We introduce R2ET which trains for stable explanation by efficient and effective regularizer, and analyze R2ET by multi-objective optimization to prove numerical and statistical stability of explanations. Moreover, theoretical connections between R2ET and certified robustness justify R2ET's stability in all attacks. Extensive experiments across various data modalities and model architectures show that R2ET achieves superior stability against stealthy attacks, and generalizes effectively across different explanation methods. The code can be found at https://***/ccha005/R2ET.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Controlling the qubit-qubit coupling in the superconducting circuit with double-resonator couplers

引用

Physical Review A 2024年第1期109卷 012601-012601页

作者： Hui Wang Yan-Jun Zhao Hui-Chen Sun Xun-Wei Xu Yong Li Yarui Zheng Qiang Liu Rengang Li Shandong Inspur Intelligence Research Institute Co. Ltd. Jinan 250100 China Shandong Yunhai Guochuang Innovative Technology Co. Ltd. Jinan 250101 China Key Laboratory of Opto-electronic Technology Ministry of Education Beijing University of Technology Beijing 100124 China Institute for Quantum Computing and Department of Physics and Astronomy University of Waterloo Waterloo Ontario N2L 3G1 Canada Key Laboratory of Low-Dimensional Quantum Structures and Quantum Control of Ministry of Education Key Laboratory for Matter Microstructure and Function of Hunan Province Department of Physics and Synergetic Innovation Center for Quantum Effects and Applications Hunan Normal University Changsha 410081 China Quantum Element Technology (Shen Zhen) Co. Ltd. Shenzhen 518048 China

We propose a theoretical scheme of using two fixed-frequency resonator couplers to tune the interaction between two Xmon qubits. The indirect interaction between two qubits induced by two resonators can cancel each other, so direct qubit-qubit coupling is not essential for the switching off. So, we can suppress the static ZZ coupling with the weak direct qubit-qubit coupling and even eliminate the static ZZ coupling through the destructive interferences of the double-path couplers. The cross-Kerr resonance can induce additional poles for the static ZZ coupling which should be kept away during the two-qubit gates. The double-resonator couplers scheme could unfreeze some restrictions during the design of superconducting quantum chips and mitigate the static ZZ coupling, which might supply a promising platform for future superconducting quantum chips.

关键词： Quantum computation Quantum control

来源：评论

学校读者我要写书评

暂无评论

A Double-Shell Structured Ransomware Defense Method Tailored for the RaaS Model 3rd

A Double-Shell Structured Ransomware Defense Method Tailored...

引用

3rd International Conference on Cyberspace Simulation and Evaluation, CSE 2024

作者： Chen, Monan Ji, Tiantian Li, Shudong Zhang, Yuntao Wang, Tian Mao, Kai Sun, Yanwei Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China Peng Cheng Laboratory Shenzhen China Zhongguancun Laboratory Beijing China

ISBN: (纸本)9789819645022

Ransomware attacks have become a significant cybersecurity threat, with the Ransomware as a service (RaaS) paradigm enabling attackers with limited technical expertise to launch sophisticated campaigns. There is currently a lack of systematic research specifically targeting RaaS-type ransomware. This paper analyzes the operational mechanisms of RaaS ransomware, including its industry chain, attack processes, and technical characteristics. We propose a formalized RaaS attack model, providing a clear understanding of its operational methods. To address the limitations of existing defense methods, we introduce an innovative double-shell structured defense model. Utilizing Hook technology and a token verification mechanism, it effectively prevents ransomware from encrypting user data. We demonstrate the effectiveness of this model through experimental validation with a document protection program named RansomShield, achieving a 100% success rate in defending against real ransomware attacks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Computer viruses

来源：评论

学校读者我要写书评

暂无评论

Majorana polarization in non-Hermitian topological superconductors

引用

Physical Review B 2021年第13期103卷 134507-134507页

作者： Zhen-Hua Wang Fuming Xu Lin Li Dong-Hui Xu Wei-Qiang Chen Bin Wang Shenzhen Key Laboratory of Advanced Thin Films and Applications College of Physics and Optoelectronic Engineering Shenzhen University Shenzhen 518060 China Center for Quantum Computing Peng Cheng Laboratory Shenzhen 518055 China College of Physics and Electronic Engineering and Center for Computational Sciences Sichuan Normal University Chengdu 610068 China Department of Physics Hubei University Wuhan 430062 China Department of Physics and Shenzhen Key Laboratory of Advanced Quantum Functional Materials and Devices Southern University of Science and Technology Shenzhen 518055 China Institute for Quantum Science and Engineering Southern University of Science and Technology Shenzhen 518055 China

Topological invariants play an important role in characterizing topological phases. However, the topological invariants of Hermitian systems usually fail to characterize non-Hermitian topological systems due to non-Hermiticity. In this work, we generalize the Majorana polarization, which is initially defined to describe Hermitian topological superconductors, as a topological edge invariant to characterize the non-Hermitian topological superconductors. The definition of the generalized Majorana polarization depends upon two inequivalent particle-hole symmetries in non-Hermitian systems. The spinless Kitaev chain model and topological superconductor model on the honeycomb lattice are considered to examine the reliability and validity of the generalized Majorana polarization. We find that the phase transitions obtained by using Majorana polarization are consistent with the commonly used complex-energy point gap descriptions, which indicates the Majorana polarization is a reliable topological invariant to characterize the topological phase transition in non-Hermitian topological superconductors. In addition, the non-Hermitian skin effect on Majorana bound states in non-Hermitian topological superconductors is also discussed.

关键词： Majorana bound states Skin effect Topological phase transition Honeycomb lattice Kitaev model Tight-binding model

来源：评论

学校读者我要写书评

暂无评论

Linear uncertainty quantification of graphical model inference 24

Linear uncertainty quantification of graphical model inferen...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Chenghua Guo Han Yu Jiaxin Liu Chao Chen Qi Li Sihong Xie Xi Zhang Key Laboratory of Trustworthy Distributed Computing and Service (MoE) Beijing University of Posts and Telecommunications China College of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Computer Science and Engineering Lehigh University School of Computer Science and Technology Harbin Institute of Technology (Shenzhen) China Department of Computer Science Iowa State University AI Thrust The Hong Kong University of Science and Technology (Guangzhou) China

ISBN: (纸本)9798331314385

Uncertainty Quantification (UQ) is vital for decision makers as it offers insights into the potential reliability of data and model, enabling more informed and risk-aware decision-making. Graphical models, capable of representing data with complex dependencies, are widely used across domains. Existing sampling-based UQ methods are unbiased but cannot guarantee convergence and are time-consuming on large-scale graphs. There are fast UQ methods for graphical models with closed-form solutions and convergence guarantee but with uncertainty underestimation. We propose LinUProp, a UQ method that utilizes a novel linear propagation of uncertainty to model uncertainty among related nodes additively instead of multiplicatively, to offer linear scalability, guaranteed convergence, and closed-form solutions without underestimating uncertainty. Theoretically, we decompose the expected prediction error of the graphical model and prove that the uncertainty computed by LinUProp is the generalized variance component of the decomposition. Experimentally, we demonstrate that LinUProp is consistent with the sampling-based method but with linear scalability and fast convergence. Moreover, LinUProp outperforms competitors in uncertainty-based active learning on four real-world graph datasets, achieving higher accuracy with a lower labeling budget.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-label Classification with High-rank and High-order Label Correlations

arXiv

引用

arXiv 2022年

作者： Si, Chongjie Jia, Yuheng Wang, Ran Zhang, Min-Ling Feng, Yanghe Qu, Chongxiao The Chien-Shiung Wu College Southeast University Nanjing210096 China The MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China The School of Computer Science and Engineering Southeast University Nanjing210096 China Ministry of Education China School of Computing & Information Sciences Caritas Institute of Higher Education Hong Kong The Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China The School of Mathematical Science Shenzhen University Shenzhen518060 China Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China The College of Systems Engineering National University of Defense Technology China The 52nd Research Institute of China Electronics Technology Group China

Exploiting label correlations is important to multi-label classification. Previous methods capture the high-order label correlations mainly by transforming the label matrix to a latent label space with low-rank matrix factorization. However, the label matrix is generally a full-rank or approximate full-rank matrix, making the low-rank factorization inappropriate. Besides, in the latent space, the label correlations will become implicit. To this end, we propose a simple yet effective method to depict the high-order label correlations explicitly, and at the same time maintain the high-rank of the label matrix. Moreover, we estimate the label correlations and infer model parameters simultaneously via the local geometric structure of the input to achieve mutual enhancement. Comparative studies over twelve benchmark data sets validate the effectiveness of the proposed algorithm in multi-label classification. The exploited high-order label correlations are consistent with common sense empirically. Our code is publicly available at https://***/Chongjie-Si/HOMI. Copyright © 2022, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Unsupervised feature selection via adaptive embedding and sparse learning for Parkinson’s disease diagnosis 1

引用

3rd International Workshop on Connectomics in NeuroImaging, CNI 2019 held in conjunction with the 22nd International Conference on Medical Image computing and Computer Assisted Intervention, MICCAI 2019

作者： Huang, Zhongwei Lei, Haijun Chen, Guoliang Li, Shiqi Li, Hancong Elazab, Ahmed Lei, Baiying Key Laboratory of Service Computing and Applications Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen518060 China

ISBN: (数字)9783030323912

ISBN: (纸本)9783030323905

Parkinson’s disease (PD) is known as a progressive neurodegenerative disease in elderly people. Apart from decelerating the disease exacerbation, early and accurate diagnosis also alleviates mental and physical sufferings and provides timely and appropriate medication. In this paper, we propose an unsupervised feature selection method via adaptive manifold embedding and sparse learning exploiting longitudinal multimodal neuroimaging data for classification and regression prediction. Specifically, the proposed method simultaneously carries out feature selection and dynamic local structure learning to obtain the structural information inherent in the neuroimaging data. We conduct extensive experiments on the publicly available Parkinson’s progression markers initiative (PPMI) dataset to validate the proposed method. Our proposed method outperforms other state-of-the-art methods in terms of classification and regression prediction performance. © Springer Nature Switzerland AG 2019.

关键词： Neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Generalized Visual Quality Assessment of GAN-Generated Face Images

arXiv

引用

arXiv 2022年

作者： Tian, Yu Ni, Zhangkai Chen, Baoliang Wang, Shiqi Wang, Hanli Kwong, Sam The Department of Computer Science City University of Hong Kong 999077 Hong Kong The Department of Computer Science & Technology Tongji University Shanghai 200092 China The Department of Computer Science & Technology Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai 200092 China The City University of Hong Kong Shenzhen Research Institute Shenzhen518057 China

Recent years have witnessed the dramatically increased interest in face generation with generative adversarial networks (GANs). A number of successful GAN algorithms have been developed to produce vivid face images towards different application scenarios. However, little work has been dedicated to automatic quality assessment of such GAN-generated face images (GFIs), even less have been devoted to generalized and robust quality assessment of GFIs generated with unseen GAN model. Herein, we make the first attempt to study the subjective and objective quality towards generalized quality assessment of GFIs. More specifically, we establish a large-scale database consisting of GFIs from four GAN algorithms, the pseudo labels from image quality assessment (IQA) measures, as well as the human opinion scores via subjective testing. Subsequently, we develop a quality assessment model that is able to deliver accurate quality predictions for GFIs from both available and unseen GAN algorithms based on meta-learning. In particular, to learn shared knowledge from GFIs pairs that are born of limited GAN algorithms, we develop the convolutional block attention (CBA) and facial attributes-based analysis (ABA) modules, ensuring that the learned knowledge tends to be consistent with human visual perception. Extensive experiments exhibit that the proposed model achieves better performance compared with the state-of-the-art IQA models, and is capable of retaining the effectiveness when evaluating GFIs from the unseen GAN algorithms. Copyright © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Robust laser self-mixing displacement demodulation viacontinuous wavelet–Hilbert transform for high-precision accelerometercalibration

引用

Applied Optics 2025年第16期64卷 4559-4567页

作者： Zhikun Chang Song Song Dongbai Xue Chunling He Zhoumiao Shi Jing Yu Ming Kong Yuying Xie Xiao Deng Tongbao Li Xinbin Cheng Institute of Precision Optical Engineering Tongji University Shanghai 200092 China National Metrology and Testing Center for Integrated Circuit Measurement and Inspection Equipment Industry (Shanghai) Tongji University Shanghai 200092 China MOE Key Laboratory of Advanced Micro-Structured Materials Tongji University Shanghai 200092 China Shanghai Frontiers Science Center of Digital Optics Tongji University Shanghai 200092 China Shanghai Professional Technical Service Platform for Full-Spectrum and High-Performance Optical Thin Film Devices and Applications Tongji University Shanghai 200092 China School of Physics Science and Engineering Tongji University Shanghai 200092 China School of Computer Science and Technology Zhejiang University of Water Resources and Electric Power Hangzhou 310018 China Shenzhen Institute of Technology Innovation NIM Shenzhen 518107 China College of Metrology and Testing Engineering China Jiliang University Hangzhou 310018 China

The laser self-mixing grating interferometer based on Cr atomlithography gratings hasbeen applied to the primarycalibration of accelerometers due to its compact structure, low cost,high accuracy, and directon-site traceability. However, the high line density of Cr gratings(4700 l/mm) introduces dense outliers in interferometricsignals, complicating displacement demodulation via conventionalderivative-based methods and causing frequent phase jumps. To addressthis challenge, we propose a hybrid algorithm integrating thecontinuous wavelet transform and the Hilbert transform, which enablesrobust displacement demodulation under high-noise *** validation on a commercial MEMS accelerometerdemonstrated exceptional accuracy: 100 consecutive data segments weresuccessfully demodulated with a displacement fitting goodness of $R^2 = 0.9964$ ( $\sigma_{R_2} =0.0027$ ), and the derived sensitivitydeviated by only 0.1% from the nominal value. This algorithmestablishes a paradigm for the high-accuracy dynamic calibration ofinertial sensors in field applications.

关键词： Laser interferometry Lithography Phase shift Refractive index Systems design Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：