检索结果-内蒙古大学图书馆

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Zhangqian Bi Yao Wan Zhaoyang Chu Yufei Hu Junyi Zhang Hongyu Zhang Guandong Xu Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science University of Technology Sydney Sydney Australia

ISBN: (数字)9798331535100

ISBN: (纸本)9798331535117

Pre-training a language model and then fine-tuning it has shown to be an efficient and effective technique for a wide range of code intelligence tasks, such as code generation, code summarization, and vulnerability detection. However, pre-training language models on a large-scale code corpus is compu-tationally expensive. Fortunately, many off-the-shelf Pre-trained Code Models (PCMs), such as CodeBERT, CodeT5, CodeGen, and Code Llama, have been released publicly. These models acquire general code understanding and generation capability during pre-training, which enhances their performance on downstream code intelligence tasks. With an increasing number of these public pre-trained models, selecting the most suitable one to reuse for a specific task is essential. In this paper, we systematically investigate the reusability of PCMs. We first explore three intuitive model selection methods that select by size, training data, or brute-force fine-tuning. Experimental results show that these straightforward techniques either perform poorly or suffer high costs. Motivated by these findings, we explore learning-based model selection strategies that utilize pre-trained models without altering their parameters. Specifically, we train proxy models to gauge the performance of pre-trained models, and measure the distribution deviation between a model's latent features and the task's labels, using their closeness as an indicator of model transferability. We conduct experiments on 100 widely-used open-source PCMs for code intelligence tasks, with sizes ranging from 42.5 million to 3 billion parameters. The results demonstrate that learning-based selection methods reduce selection time to 100 seconds, compared to 2,700 hours with brute-force fine-tuning, with less than 6% performance degradation across related tasks.

关键词： Phase change materials Analytical models Adaptation models Codes Costs Computational modeling Training data Machine learning Software Software development management

来源：评论

学校读者我要写书评

暂无评论

Efficient Federated Recommender system with Adaptive Model Pruning and Momentum-based Batch Adjustment

引用

ACM Transactions on Recommender systems 2025年第3期3卷 1-23页

作者： Hongjian Shi Yicheng Di Xinyu Ruan Mingrui Liao Qian Zhang Ruhui Ma Haibing Guan School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi China School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Aerospace System Engineering Shanghai Shanghai China

With the development of 5G communication and smart devices, the prosperity of online content has boosted Recommender system (RS) research. Due to the data scarcity problem, researchers employ knowledge transfer techniques to improve the accuracy of RS. Data sharing or data augmentation are promising methods for such a problem, but the data suffers from privacy leakage during sharing. Thus, federated learning has been adopted to collaboratively train recommender models while preserving data privacy. Federated Recommender system (FRS) combines federated learning and RS to provide distributed recommendation services to the users. However, the existing FRS suffers from massive communication and system heterogeneity, where the necessity of model transmission and the diversity of the clients bring significant communication overhead to the system. In this article, we propose Efficient Federated Recommender system with Adaptive Model Pruning and Momentum-based Batch Adjustment (\(eFRSA^{2}\)) to reduce the communication overhead of FRS. \(eFRSA^{2}\) contains two modules. Adaptive Model Pruning utilizes magnitude pruning to reduce the communication volume and adaptively modifies the compression ratios of different clients to maintain the model accuracy. Momentum-based Batch Adjustment adjusts the local training batch number by a similar method of gradient descent with momentum to align the local computation time of the clients and reduce the communication overhead. The experimental results demonstrate that \(eFRSA^{2}\) can reduce up to 90% communication volume and mitigate the system heterogeneity by over 75%, demonstrating the priority of \(eFRSA^{2}\) in training efficiency. Source code can be found at https://***/shhjwu5/eFRSA2.

关键词： Federated learning recommender system model pruning batch adjustment

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

DENSE-Guided Deep Motion Networks Accounted by Large Rotations to Improve Myocardial Strain Analysis from Routine Cine MRI

DENSE-Guided Deep Motion Networks Accounted by Large Rotatio...

引用

IEEE International Symposium on Biomedical Imaging

作者： Pengcheng Lei Jiarui Xing Faming Fang Frederick H. Epstein Miaomiao Zhang Department of Electrical and Computer Engineering University of Virginia USA School of Computer Science and Technology East China Normal University Shanghai China Department of Biomedical Engineering University of Virginia Health System USA

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Myocardial strain imaging provides a valuable tool for detecting subclinical left ventricular (LV) dysfunction and adding prognostic value in assessing various types of heart disease. Recent studies have utilized highly accurate strain-dedicated techniques, such as displacement encoding with stimulated echoes (DENSE), to train a deep learning (DL) framework to predict the myocardial displacements/deformations from routine cine balanced steady state free precession (bSSFP) images. However, these methods have shown limited performance in capturing the large rotational motion of the myocardium associated with twist and torsion over time, which are important aspects of myocardial mechanics. To address this gap, this paper introduces a novel DENSE-guided DL network that explicitly accounts for large rotational motion to further improve strain analysis of standard cine bSSFP images. Specifically, our proposed network includes two key components: (i) a time-series rotation estimation network employing a 3D convolutional encoder-decoder architecture to model the large rotational dynamics of the LV myocardium over time, and (ii) a radial motion prediction network based on deformable image registration. The output of these two sub-networks was integrated and refined through a fusion network to predict the final myocardial displacements, supervised by DENSE ground truth. Experimental results show that our method improves the accuracy of myocardial strain with effectively captured large rotations.

关键词： Deep learning Solid modeling Accuracy Three-dimensional displays Magnetic resonance imaging Myocardium Predictive models Steady-state Standards Strain

来源：评论

学校读者我要写书评

暂无评论

PB-UAP: Hybride Universal Adversarial Attack for Image Segmentation

PB-UAP: Hybride Universal Adversarial Attack for Image Segme...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yufei Song Ziqi Zhou Minghui Li Xianlong Wang Hangtao Zhang Menghao Deng Wei Wan Shengshan Hu Leo Yu Zhang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

With the rapid advancement of deep learning, the model robustness has become a significant research hotspot, i.e., adversarial attacks on deep neural networks. Existing works primarily focus on image classification tasks, aiming to alter the model’s predicted labels. Due to the output complexity and deeper network architectures, research on adversarial examples for segmentation models is still limited, particularly for universal adversarial perturbations. In this paper, we propose a novel universal adversarial attack method designed for segmentation models, which includes dual feature separation and low-frequency scattering modules. The two modules guide the training of adversarial examples in the pixel and frequency space, respectively. Experiments demonstrate that our method achieves high attack success rates surpassing the state-of-the-art methods, and exhibits strong transferability across different models.

关键词： Training Image segmentation Perturbation methods Semantics Scattering Signal processing Predictive models Network architecture Robustness Speech processing

来源：评论

学校读者我要写书评

暂无评论

Neural network-driven parallel accelerated selective image encryption with semantic understanding

引用

The European Physical Journal Special Topics 2025年 1-16页

作者： Song, Wei Fu, Chong Zheng, Yu Chen, Junxin Zhang, Yanfeng School of Computer Science and Engineering Northeastern University Shenyang China Engineering Research Center of Security Technology of Complex Network System Ministry of Education Shenyang China University of California Irvine Irvine USA School of Software Dalian University of Technology Dalian China

Existing batch image encryption schemes often directly encrypt images without considering their source. However, in real-life scenarios, these images are typically part of a larger collection stored in a directory on a computer or in the cloud. To efficiently protect those sensitive images distributed within the collection, we rethink selective image encryption (SIE) from the perspective of batch image encryption and proposes a novel SIE scheme using deep neural networks (DNN) and parallel computing. First, a DNN method is employed to identify sensitive images by analyzing their semantics. Next, a parallel cross-bitplane permutation algorithm is introduced to shuffle the retrieved images in bit-level. Then, a bi-directional diffusion strategy is employed to spread the encryption influence of a pixel to all images. Experimental results demonstrate the proposed scheme effectively understands the semantic of images, identifies sensitive images, and encrypts them with high permutation and diffusion efficiency. Further security analyses show that the proposed algorithm successfully resists various attacks with desired performance, including achieving high information entropy and low correlation coefficients in statistical analysis, and ideal values of the number of pixels changing rate (NPCR) and the unified averaged changing intensity (UACI) to resist differential attack, as well as high key sensitivity.

关键词：

来源：评论

学校读者我要写书评

暂无评论

PSMiner: A Pattern-Aware Accelerator for High-Performance Streaming Graph Pattern Mining 23

PSMiner: A Pattern-Aware Accelerator for High-Performance St...

引用

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

作者： Hao Qi Yu Zhang Ligang He Kang Luo Jun Huang Haoyu Lu Jin Zhao Hai Jin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China and Zhejiang-HUST Joint Research Center for Graph Processing Zhejiang Lab China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798350323481

Streaming Graph Pattern Mining (GPM) has been widely used in many application fields. However, the existing streaming GPM solution suffers from many unnecessary explorations and isomorphism tests, while the existing static GPM ones require many repetitive operations to compute the full graph. In this paper, we propose a pattern-aware incremental execution approach and design the first streaming GPM accelerator called PSMiner, which integrates multiple optimizations to reduce redundant computation and improve computing efficiency. We have conducted extensive experiments. The results show that compared with the state-of-the-art software and hardware solutions, PSMiner achieves the average speedups of 770.9× and 60.4×, respectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resilient Cooperative Control of Multiple DC Microgrids With Interconnection Networks Against Cyber Attacks

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical systems 2025年 3卷 116-126页

作者： Xiao, Feng Liu, Shiyu Wei, Bo Fang, Fang Qin, Jiahu North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources Beijing102206 China North China Electric Power University School of Control and Computer Engineering Beijing102206 China North China Electric Power University New Energy Generation National Engineering Research Center Beijing102206 China University of Science and Technology of China Department of Automation Hefei230027 China

The two control objectives of voltage regulation and precise current sharing are conflicting in multi-bus DC microgrids. In this paper, a distributed control strategy is proposed, and it can achieve accurate current sharing and regulate the voltage of a critical node to the rated value. However, such a distributed control system is susceptible to potential cyber attacks that could deteriorate microgrids performances by corrupting communication links or actuators. To overcome these difficulties, we design the interconnected communication networks to establish a resilient cooperative system of multiple microgrids against unknown bounded injection attacks. The proposed resilient control strategy can achieve the control objectives of maintaining voltage regulation and current sharing within each microgrids under different operating conditions, and the interconnected system consisting of multiple microgrids cooperates to mitigate the adverse effect of cyber attacks. The dynamics and stability of the overall close-loop system of the DC microgrids are analyzed, in the present or absent of cyber attacks. Simulation results validate the effectiveness of the proposed approach in two 4-bus DC microgrids. © 2023 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

EdgeThemis: Ensuring Model Integrity for Edge Intelligence 25

EdgeThemis: Ensuring Model Integrity for Edge Intelligence

引用

34th ACM Web Conference, WWW 2025

作者： Yang, Jiyu He, Qiang Zhou, Zheyu Dai, Xiaohai Chen, Feifei Tian, Cong Yang, Yun Swinburne University of Technology Melbourne Australia Huazhong University of Science and Technology Wuhan China Deakin University Melbourne Australia Xidian University Xi’an China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9798400712746

Machine learning (ML) models are widely deployed on edge nodes, such as mobile phones and edge servers, to power a wide range of AI applications over the web. Ensuring the integrity of these edge models is paramount, as they are subject to corruption caused by software/hardware exceptions and malicious tampering, which may undermine model performance, incur economic losses, and pose health risks. Existing data integrity mechanisms designed for files stored on disks cannot properly verify the integrity of models running in GPUs or mitigate the new integrity threats against edge models. This paper proposes EdgeThemis, a novel mechanism for verifying the integrity of edge models through sentinel verification. To enable verifiability for a model M, EdgeThemis embeds a sentinel backdoor and a verification module into M. Then, a challenger can send verification requests to the edge node hosting M to verify its integrity. Next, the sentinel activates the verification module to generate a unique integrity proof tied to the identity of the edge node for verification. Finally, the challenger can verify the integrity proof to detect model corruption. Theoretical analysis proves that EdgeThemis can properly mitigate potential integrity threats against edge models. Experiments demonstrate that EdgeThemis achieves a verification accuracy of 100.00% across various models and different types of model corruption with robustness against replay attacks, theft attacks, and replacement attacks. © 2025 Copyright held by the owner/author(s).

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Listwise ranking predictor for evolutionary neural architecture search

引用

Swarm and Evolutionary Computation 2025年 96卷

作者： Li, Nan Ma, Lianbo Wang, Rui Cheng, Shi Sun, Yanan Xue, Bing Zhang, Mengjie College of Software Northeastern University Liaoning Shenyang110819 China Centre for Data Science and Artificial Intelligence & School of Engineering and Computer Science Victoria University of Wellington Wellington 6140 New Zealand Foshan Graduate School of Innovation Guangdong Foshan528000 China College of System Engineering National University of Defense Technology Hunan Changsha410073 China School of Computer Science Shaanxi Normal University Shaanxi Xian710119 China School of Computer Science Sichuan University Sichuan Chengdu610000 China

In evolutionary neural architecture search (ENAS), the accuracy predictors (i.e., regression models) have been successfully applied to save computational costs for the evaluation of network architectures. However, the accuracy of these predictors is largely limited by the small amount of evaluated architectures that may be difficult to obtain. Such accuracy predictors with prediction bias often lead to an inaccurate ranking, misleading the selection of ENAS. To alleviate the above limitations, we design an efficient and novel listwise ranking predictor (LRP) for ENAS to directly predict the ranking of each architecture instead of the numerical accuracy value of each architecture. Specifically, the training data is constructed by the proposed random encoding-combination (REC) strategy, which can generate substantial training data using the small number of evaluated architectures (data level). These specially constructed training data are used to train LRP, which can convert the complex regression task into a ranking task to reduce ranking bias (model level). The proposed NAS method is compared with state-of-the-art NAS methods on widely-used benchmark datasets and practical application. Experimental results demonstrate that LRP can alleviate the ranking disorder problem and outperform others in terms of both effectiveness and efficiency. © 2025 Elsevier B.V.

关键词： Linear regression

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：