检索结果-内蒙古大学图书馆

RE-SEGNN:recurrent semantic evidence-aware graph neural network for temporal knowledge graph forecasting

Science China(Information Sciences) 2025年第2期68卷 103-119页

作者： Wenyu CAI Mengfan LI Xuanhua SHI Yuanxin FAN Quntao ZHU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and Technology

Temporal knowledge graph(TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both entity and relation embedding to make predictions, ignoring the semantic correlations among different entities and relations within the same timestamp. This can lead to random and nonsensical predictions when unseen entities or relations occur. Furthermore, many existing models exhibit limitations in handling highly correlated historical facts with extensive temporal depth. They often either overlook such facts or overly accentuate the relationships between recurring past occurrences and their current counterparts. Due to the dynamic nature of TKG, effectively capturing the evolving semantics between different timestamps can be *** address these shortcomings, we propose the recurrent semantic evidenceaware graph neural network(RE-SEGNN), a novel graph neural network that can learn the semantics of entities and relations simultaneously. For the former challenge, our model can predict a possible answer to missing quadruples based on semantics when facing unseen entities or relations. For the latter problem, based on an obvious established force, both the recency and frequency of semantic history tend to confer a higher reference value for the current. We use the Hawkes process to compute the semantic trend, which allows the semantics of recent facts to gain more attention than those of distant facts. Experimental results show that RE-SEGNN outperforms all SOTA models in entity prediction on 6 widely used datasets, and 5 datasets in relation prediction. Furthermore, the case study shows how our model can deal with unseen entities and relations.

关键词： knowledge graph reasoning temporal knowledge graph Hawkes process semantic evidence

来源：评论

学校读者我要写书评

暂无评论

EPCNN: Efficient and Practical Privacy-Preserving Convolutional Neural Network Inference

引用

IEEE Transactions on Network Science and engineering 2025年第3期12卷 1567-1580页

作者： He, Gang Ren, Yanli Zhao, Jun Feng, Guorui Zhang, Xinpeng Shanghai University School of Communication and Information Engineering Shanghai200444 China Nanyang Technological University School of Computing and Data Science 639798 Singapore

Convolutional Neural Networks (CNNs), as a powerful tool for efficient inference, have rapidly developed into a Machine Learning as a Service paradigm facilitated by cloud computing. Nevertheless, this service model raises privacy concerns, particularly in scenarios where relying on two non-colluding servers is unfeasible. To address this issue, we present EPCNN, an Efficient and Practical CNN inference scheme, which concurrently ensures data privacy, model privacy, and inference results with only a single server. EPCNN leverages Paillier homomorphic encryption for secure convolution operations on encrypted data and involves minimal client-server interactions. The client only participates in evaluating non-linear activation functions by judging the signs of blinded convolution results to streamline the interactions and enhance the system's practicality. Our security analysis validates the reliability of the proposed scheme, while experimental results demonstrate high inference accuracy comparable to plaintext-based methods. Compared to the state-of-the-art work, EPCNN attains huge improvements in both runtime and communication overhead. © 2013 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

LaserKey: Eavesdropping Keyboard Typing Leveraging Vibrational Emanations via Laser Sensing

引用

IEEE Transactions on Mobile computing 2025年第6期24卷 4829-4844页

作者： Luo, Chengwen Xie, Zhuoqing Huang, Yuhan Chen, Gecheng Yao, Haiyi Zhang, Jin Cheng, Long Xu, Weitao Li, Jianqiang National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China School of Computing Clemson University United States City University of Hong Kong Hong Kong

Reconstructing keyboard input through side-channel attacks has posed significant threats to user security. While conventional keystroke eavesdropping attacks have demonstrated effectiveness using side channels such as acoustic signals, they are usually shorter in range and can be significantly affected by environmental noises. In this paper, we propose LaserKey, a novel keystroke eavesdropping technique that leverages the long-range and noise-resistant nature of lasers to achieve a more stealthy side-channel attack. We utilize laser sensors to accurately capture the subtle vibrations induced on laptop screens by keystrokes, and innovatively design a laser-driven deep learning-based keystroke recognition model with the inputs being the Mel-frequency Cepstral Coefficien (MFCC), Time Difference of Arrival (TDoA), and amplitude features extracted from such vibration signals. Through systematic experiments, we demonstrate that LaserKey achieves a 92.2% single-key recognition accuracy. By combining multiple single-key recognition capabilities based on this, we then realize the end-to-end word-level recognition. Moreover, to mitigate the recognition errors caused by the changes in keystroke positions, we introduce a meta-learning based domain generalization approach for achieving robust laser position calibration. Results show that LaserKey achieves as low as 3% character error rate (CER) for word-level recognition, proving its effectiveness for long-range and high-accuracy keystroke eavesdropping, and highlighting the necessity for countermeasures in the future. © 2002-2012 IEEE.

关键词： Systematic errors

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-Calibrated Test-Time Model Adaptation without Forgetting

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 1-14页

作者： Tan, Mingkui Chen, Guohao Wu, Jiaxiang Zhang, Yifan Chen, Yaofo Zhao, Peilin Niu, Shuaicheng South China University of Technology School of Software Engineering China Pazhou Laboratory Guangzhou China XVERSE China National University of Singapore School of Computing Singapore Tencent AI Lab China Nanyang Technological University College of Computing and Data Science Singapore

Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important when the test environment changes frequently. Although some recent attempts have been made to handle this task, we still face two key challenges: 1) prior methods have to perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications;2) while existing TTA solutions can significantly improve the test performance on out-of-distribution data, they often suffer from severe performance degradation on in-distribution data after TTA (known as catastrophic forgetting). To this end, we have proposed an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples for test-time entropy minimization. To alleviate forgetting, EATA introduces a Fisher regularizer estimated from test samples to constrain important model parameters from drastic changes. However, in EATA, the adopted entropy loss consistently assigns higher confidence to predictions even when the samples are underlying uncertain, leading to overconfident predictions that underestimate the data uncertainty. To tackle this, we further propose EATA with Calibration (EATA-C) to separately exploit the reducible model uncertainty and the inherent data uncertainty for calibrated TTA. Specifically, we compare the divergence between predictions from the full network and its sub-networks to measure the reducible model uncertainty, on which we propose a test-time uncertainty reduction strategy with divergence minimization loss to encourage consistent predictions instead of overconfident ones. To further re-calibrate predicting confidence on different samples, we utilize the disagreement among predicted labels as an indicator of the data uncertainty. Based on this, we devise a min-max entropy

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Detecting the symptoms of COVID-19 during pandemic environment using smart spectacle thermal images and deep capsule networks

引用

Multimedia Tools and Applications 2025年第8期84卷 4475-4501页

作者： Dwarakanath, B. Pandimurugan, V. Mohandas, R. Sambath, M. Baiju, B.V. Chinnasamy, A. SRM Institute of Science and Technology Ramapuram Chennai India Networking and Communications School of Computing SRMIST kattankulathur Chennai India Computational Intelligence School of Computing SRMIST kattankulathur Chennai India Computer Science and Engineering Hindustan Institute of Technology and Science Chennai India School of Computer Science and Engineering Vellore Institute of Technology Vellore India Department of Data Science and Business Systems School of Computing SRMIST kattankulathur Chennai India

The pandemic creates a more complicated providence of medical assistance and diagnosis procedures. In the world, Covid-19, Severe Acute Respiratory Syndrome Coronavirus-2 (SARS Cov-2), and plague are widely known pandemic disease desperations. Due to the recent COVID-19 pandemic tragedies, various medical diagnosis models and intelligent computing solutions are proposed for medical applications. In this era of computer-based medical environment, conventional clinical solutions are surpassed by many Machine Learning and Deep Learning-based COVID-19 diagnosis models. Anyhow, many existing models are developing lab-based diagnosis environments. Notably, the Gated Recurrent Unit-based Respiratory data Analysis (GRU-RE), Intelligent Unmanned Aerial Vehicle-based Covid data Analysis (Thermal Images) (I-UVAC), and Convolutional Neural Network-based Computer Tomography Image Analysis (CNN-CT) are enriched with lightweight image data analysis techniques for obtaining mass pandemic data at real-time conditions. However, the existing models directly deal with bulk images (thermal data and respiratory data) to diagnose the symptoms of COVID-19. Against these works, the proposed spectacle thermal image data analysis model creates an easy and effective way of disease diagnosis deployment strategies. Particularly, the mass detection of disease symptoms needs a more lightweight equipment setup. In this proposed model, each patient's thermal data is collected via the spectacles of medical staff, and the data are analyzed with the help of a complex set of capsule network functions. Comparatively, the conventional capsule network functions are enriched in this proposed model using adequate sampling and data reduction solutions. In this way, the proposed model works effectively for mass thermal data diagnosis applications. In the experimental platform, the proposed and existing models are analyzed in various dimensions (metrics). The comparative results obtained in the experiments just

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario

引用

IEEE Transactions on Multimedia 2025年 27卷 2666-2681页

作者： Liu, Renyang Lam, Kwok-Yan Zhou, Wei Wu, Sixing Zhao, Jun Hu, Dongting Gong, Mingming Yunnan University School of Information Science and Engineering Kunming650500 China Nanyang Technological University College of Computing and Data Science 639798 Singapore Yunnan University School of Software Engineering Research Center of Cyberspace Kunming650500 China University of Melbourne Melbourne Centre for Data Science School of Mathematics and Statistics ParkvilleVIC3010 Australia

Extensive studies have revealed that deep neural networks (DNNs) are vulnerable to adversarial attacks, especially black-box ones, which can heavily threaten the DNNs deployed in the real world. Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness. Despite the significant progress made recently, existing black-box attack methods still suffer from unsatisfactory performance due to the vast number of queries needed to optimize desired perturbations. Besides, the other critical challenge is that adversarial examples built in a noise-adding manner are abnormal and struggle to successfully attack robust models, whose robustness is enhanced by adversarial training against small perturbations. There is no doubt that these two issues mentioned above will significantly increase the risk of exposure and result in a failure to dig deeply into the vulnerability of DNNs. Hence, it is necessary to evaluate DNNs' fragility sufficiently under query-limited settings in a non-additional way. In this paper, we propose the Spatial Transform Black-box Attack (STBA), a novel framework to craft formidable adversarial examples in the query-limited scenario. Specifically, STBA introduces a flow field to the high-frequency part of clean images to generate adversarial examples and adopts the following two processes to enhance their naturalness and significantly improve the query efficiency: a) we apply an estimated flow field to the high-frequency part of clean images to generate adversarial examples instead of introducing external noise to the benign image, and b) we leverage an efficient gradient estimation method based on a batch of samples to optimize such an ideal flow field under query-limited settings. Compared to existing score-based black-box baselines, extensive experiments indicated that STBA could effectively improve the imperceptibility of the adversarial examples and remarkably boost the attack success rate u

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Cost-Effective Edge data Caching with Failure Tolerance and Popularity Awareness

引用

IEEE Transactions on Mobile computing 2025年第6期24卷 5357-5369页

作者： Luo, Ruikun Zhang, Zujia He, Qiang Xu, Mengxi Chen, Feifei Dai, Xiaohai Wu, Song Jin, Hai Huazhong University of Science and Technology 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 China Deakin University School of Information Technology GeelongVIC3125 Australia

In the mobile edge computing environment, caching data in edge storage systems can significantly reduce data retrieval latency for users while saving the costs incurred by cloud-edge data transmissions for app vendors. Existing edge data caching (EDC) methods prioritize popular data and aim to minimize users' data retrieval latency and system storage costs jointly. However, these EDC methods often rely on the assumption that data popularity always follows certain distributions. As a result, they cannot properly adapt to the fluctuations in data popularity due to user mobility or unexpected increases in user demands. Meanwhile, unlike cloud data centers, complex and fragile edge servers are more likely to experience physical failures or network outages, presenting new challenges for EDC strategies. Specifically, when an edge server fails or experiences an outage, cached data may become temporarily unavailable, leading to increased latency as requests are redirected to alternative servers or the cloud. In this paper, to enable uncertainty-aware edge data caching (uEDC), we first model the problem as a robust optimization problem and propose an optimal algorithm named uEDC-B to find the optimal uEDC solution. To address the high computational complexity of uEDC-B, we introduce an approximate algorithm named uEDC-L based on linear decision rules. Theoretical analysis and extensive experiments on a real-world dataset demonstrate that the proposed methods outperform two state-of-the-art approaches in handling the uncertainties in data popularity and edge server failure with a significant performance improvement of 59.27% in data retrieval latency and 55.07% in data caching cost. © 2002-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

A HIGH ORDER SCHEME FOR FRACTIONAL DIFFERENTIAL EQUATIONS WITH THE CAPUTO-HADAMARD DERIVATIVE

引用

Journal of Computational Mathematics 2025年第3期43卷 615-640页

作者： Xingyang Ye Junying Cao Chuanju Xu School of Science Jimei UniversityXiamen 361021China School of Data Science and Information Engineering Guizhou Minzu UniversityGuiyang 550025China School of Mathematical Sciences and Fujian Provincial Key Laboratory of Mathematical Modeling and High Performance Scientific Computing Xiamen UniversityXiamen 361005China

In this paper,we consider numerical solutions of the fractional diffusion equation with theαorder time fractional derivative defined in the Caputo-Hadamard sense.A high order time-stepping scheme is constructed,analyzed,and numerically *** contribution of the paper is twofold:1)regularity of the solution to the underlying equation is investigated,2)a rigorous stability and convergence analysis for the proposed scheme is performed,which shows that the proposed scheme is 3+αorder *** numerical examples are provided to verify the theoretical statement.

关键词： Caputo-Hadamard derivative Fractional differential equations High order scheme Stability and convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Retrieval-Augmented Fine-Tuning for Improving Retrieve-and-Edit Based Assertion Generation

引用

IEEE Transactions on Software engineering 2025年第05期51卷 1591-1614页

作者： Li, Hongyan Sun, Weifeng Yan, Meng Xu, Ling Li, Qiang Zhang, Xiaohong Zhang, Hongyu Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Ministry of Education Chongqing400044 China School of Big Data and Software Engineering Chongqing University Chongqing400044 China

Unit Testing is crucial in software development and maintenance, aiming to verify that the implemented functionality is consistent with the expected functionality. A unit test is composed of two parts: a test prefix, which drives the unit under test to a particular state, and a test assertion, which determines what the expected behavior is under that state. To reduce the effort of conducting unit tests manually, Yu et al. proposed an integrated approach (integration for short), combining information retrieval with a deep learning-based approach to generate assertions for test prefixes, and obtained promising results. In our previous work, we found that the overall performance of integration is mainly due to its success in retrieving assertions. Moreover, integration is limited to specific types of edit operations and struggles to understand the semantic differences between the retrieved focal-test (focal-test includes a test prefix and a unit under test) and the input focal-test. Based on these insights, we then proposed a retrieve-and-edit approach named EditAS to learn the assertion edit patterns to improve the effectiveness of assertion generation in our prior study. Despite being promising, we find that the effectiveness of EditAS can be further improved. Our analysis shows that: ① The editing ability of EditAS still has ample room for improvement. Its performance degrades as the edit distance between the retrieval assertion and ground truth increases. Specifically, the average accuracy of EditAS is 12.38% when the edit distance is greater than 5. ② EditAS lacks a fine-grained semantic understanding of both the retrieved focal-test and the input focal-test themselves, which leads to many inaccurate token modifications. In particular, an average of 25.57% of the incorrectly generated assertions that need to be modified are not modified, and an average of 6.45% of the assertions that match the ground truth are still modified. Thanks to pre-trained models employing

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Reasoning with Trees: Faithful Question Answering over Knowledge Graph 31

Reasoning with Trees: Faithful Question Answering over Knowl...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Shen, Tiesunlong Wang, Jin Zhang, Xuejie Cambria, Erik School of Information Science and Engineering Yunnan University Kunming China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)9798891761964

Recent advancements in large language models (LLMs) have shown remarkable progress in reasoning capabilities, yet they still face challenges in complex, multi-step reasoning tasks. This study introduces Reasoning with Trees (RwT), a novel framework that synergistically integrates LLMs with knowledge graphs (KGs) to enhance reasoning performance and interpretability. RwT reformulates knowledge graph question answering (KGQA) as a discrete decision-making problem, leveraging Monte Carlo Tree Search (MCTS) to iteratively refine reasoning paths. This approach mirrors human-like reasoning by dynamically integrating the LLM's internal knowledge with external KG information. We propose a real-data guided iteration technique to train an evaluation model that assesses action values, improving the efficiency of MCTS. Experimental results on two benchmark KGQA datasets demonstrate that RwT significantly outperforms existing state-of-the-art methods, with an average performance improvement of 9.81%. Notably, RwT achieves these improvements without requiring complete LLM retraining, offering a more efficient and adaptable approach to enhancing LLM reasoning capabilities. © 2025 Association for Computational Linguistics.

关键词： Knowledge graph

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：