检索结果-内蒙古大学图书馆

2025 2nd International Conference on Algorithms, Software engineering and Network Security (ASENS)

作者： Songbo Wang Yifan Chen Haizhi Xu Jianqiao Hu Peiyu Zeng Ziming Hu School of Computing and Data Science The University of Hong Kong Hong Kong China School of Microelectronics Science and Technology Sun Yat-sen University Zhuhai China School of Software Engineering South China University of Technology Guangzhou China School of Materials Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798331520298

ISBN: (纸本)9798331520304

Spatio-temporal series forecasting plays a vital role in the domain of multivariate time series prediction. By leveraging accurate and comprehensive spatio-temporal sequence prediction models, it becomes possible to extract higher-order spatio-temporal interactions between real-world connections, thereby contributing to smart city construction. Spatio-Temporal Graph Neural Networks (STGNNs) have emerged as a highly effective approach for addressing spatio-temporal series prediction challenges. Nevertheless, most existing methods predominantly rely on traditional graph convolutional networks (GCNs) and their variants for spatial feature extraction. Due to inherent limitations such as over-smoothing, these models often constrain spatial feature encoding to shallow architectures, typically limited to 2-3 layers. Additionally, the presence of noisy data in real-world scenarios significantly impacts the prediction accuracy of existing STGNN models. In this paper, building upon the classic STGNN framework, we propose a graph neural network framework based on deep residual connections and noise injection mechanism to address the aforementioned issues. Specifically, inspired by the principles of initial residual connection and identity mapping, we proposed a deep spatio-temporal graph neural network framework of 12 layers to capture the high-dimensional interactions, while using noise injection mechanism to mitigate the adverse effects of noisy data. Sufficient experimental results on typical time-series datasets demonstrate the effectiveness of our proposed framework.

关键词： Accuracy Noise Time series analysis Predictive models Feature extraction Transformers Graph neural networks Spatiotemporal phenomena Noise measurement Forecasting

来源：评论

学校读者我要写书评

暂无评论

Monge-Ampere Regularization for Learning Arbitrary Shapes from Point Clouds

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年

作者： Yang, Chuanxiang Zhou, Yuanfeng Wei, Guangshun Ma, Long Hou, Junhui Liu, Yuan Wang, Wenping The School of Software Shandong University Jinan250100 China The Department of Computer Science City University of Hong Kong Hong Kong The College of Computing and Data Science Nanyang Technological University Singapore The Department of Computer Science and Engineering Texas A&M University College StationTX77843 United States

As commonly used implicit geometry representations, the signed distance function (SDF) is limited to modeling watertight shapes, while the unsigned distance function (UDF) is capable of representing various surfaces. However, its inherent theoretical shortcoming, i.e., the non-differentiability at the zero-level set, would result in sub-optimal reconstruction quality. In this paper, we propose the scaled-squared distance function (S2DF), a novel implicit surface representation for modeling arbitrary surface types. S2DF does not distinguish between inside and outside regions while effectively addressing the non-differentiability issue of UDF at the zero-level set. We demonstrate that S2DF satisfies a second-order partial differential equation of Monge-Ampere-type, allowing us to develop a learning pipeline that leverages a novel Monge-Ampere regularization to directly learn S2DF from raw unoriented point clouds without supervision from ground-truth S2DF values. Extensive experiments across multiple datasets show that our method significantly outperforms state-of-the-art supervised approaches that require ground-truth surface information as supervision for training. The code will be publicly available at https://***/chuanxiang-yang/S2DF. © 2025 IEEE. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards Context-aware Support for Color Vision Deficiency: An Approach Integrating LLM and AR

arXiv

引用

arXiv 2024年

作者： Morita, Shogo Zhang, Yan Yamauchi, Takuto Chen, Sinan Li, Jialong Tei, Kenji School of Computing Tokyo Institute of Technology Tokyo Japan International Research Center for Neurointelligence the University of Tokyo Tokyo Japan Department of Computer Science and Engineering Waseda University Tokyo Japan Center of Mathematical and Data Sciences Kobe University Kobe Japan

People with color vision deficiency often face challenges in distinguishing colors such as red and green, which can complicate daily tasks and require the use of assistive tools or environmental adjustments. Current support tools mainly focus on presentation-based aids, like the color vision modes found in iPhone accessibility settings. However, offering context-aware support, like indicating the doneness of meat, remains a challenge since task-specific solutions are not cost-effective for all possible scenarios. To address this, our paper proposes an application that provides contextual and autonomous assistance. This application is mainly composed of: (i) an augmented reality interface that efficiently captures context;and (ii) a multi-modal large language model-based reasoner that serves to cognitize the context and then reason about the appropriate support contents. Preliminary user experiments with two color vision deficient users across five different scenarios have demonstrated the effectiveness and universality of our application. © 2024, CC BY.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Toward Democratized Generative AI in Next-Generation Mobile Edge Networks

arXiv

引用

arXiv 2024年

作者： Zhang, Ruichen He, Jiayi Luo, Xiaofeng Niyato, Dusit Kang, Jiawen Xiong, Zehui Li, Yonghui Sikdar, Biplab The College of Computing and Data Science Nanyang Technological University Singapore The School of Automation Guangdong University of Technology Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The School of Electrical and Information Engineering University of Sydney SydneyNSW2006 Australia The Department of Electrical and Computer Engineering College of Design and Engineering National University of Singapore Singapore

The rapid development of generative AI technologies, including large language models (LLMs), has brought transformative changes to various fields. However, deploying such advanced models on mobile and edge devices remains challenging due to their high computational, memory, communication, and energy requirements. To address these challenges, we propose a model-centric framework for democratizing generative AI deployment on mobile and edge networks. First, we comprehensively review key compact model strategies, such as quantization, model pruning, and knowledge distillation, and present key performance metrics to optimize generative AI for mobile deployment. Next, we provide a focused review of mobile and edge networks, emphasizing the specific challenges and requirements of these environments. We further conduct a case study demonstrating the effectiveness of these strategies by deploying LLMs on real mobile edge devices. Experimental results highlight the practicality of democratized LLMs, with significant improvements in generalization accuracy, hallucination rate, accessibility, and resource consumption. Finally, we discuss potential research directions to further advance the deployment of generative AI in resource-constrained environments. © 2024, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Contamination-resilient anomaly detection via adversarial learning on partially-observed normal and anomalous data 24

Contamination-resilient anomaly detection via adversarial le...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Wenxi Lv Qinliang Su Hai Wan Hongteng Xu Wenchao Xu School of Computer Science and Engineering Sun Yat-sen University Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Gaoling School of Artifical Intelligence Renmin University of China Beijing China Department of Computing The Hong Kong Polytechnic University Hong Kong SAR

Many existing anomaly detection methods assume the availability of a large-scale normal dataset. But for many applications, limited by resources, removing all anomalous samples from a large unlabeled dataset is unrealistic, resulting in contaminated datasets. To detect anomalies accurately under such scenarios, from the probabilistic perspective, the key question becomes how to learn the normal-data distribution from a contaminated dataset. To this end, we propose to collect two additional small datasets that are comprised of partially-observed normal and anomaly samples, and then use them to help learn the distribution under an adversarial learning scheme. We prove that under some mild conditions, the proposed method is able to learn the correct normal-data distribution. Then, we consider the overfitting issue caused by the small size of the two additional datasets, and a correctness-guaranteed flipping mechanism is further developed to alleviate it. Theoretical results under incomplete observed anomaly types are also presented. Extensive experimental results demonstrate that our method outperforms representative baselines when detecting anomalies under contaminated datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Effectiveness of Function-Level Vulnerability Detectors for Inter-Procedural Vulnerabilities

arXiv

引用

arXiv 2024年

作者： Li, Zhen Wang, Ning Zou, Deqing Li, Yating Zhang, Ruqian Xu, Shouhuai Zhang, Chao Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Computer Science University of Colorado Colorado Springs Colorado SpringsCO United States Institute for Network Sciences and Cyberspace Tsinghua University Beijing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab China JinYinHu Laboratory Wuhan China

Software vulnerabilities are a major cyber threat and it is important to detect them. One important approach to detecting vulnerabilities is to use deep learning while treating a program function as a whole, known as function-level vulnerability detectors. However, the limitation of this approach is not understood. In this paper, we investigate its limitation in detecting one class of vulnerabilities known as inter-procedural vulnerabilities, where the to-be-patched statements and the vulnerability-triggering statements belong to different functions. For this purpose, we create the first Inter-Procedural Vulnerability dataset (InterPVD) based on C/C++ open-source software, and we propose a tool dubbed VulTrigger for identifying vulnerability-triggering statements across functions. Experimental results show that VulTrigger can effectively identify vulnerability-triggering statements and inter-procedural vulnerabilities. Our findings include: (i) inter-procedural vulnerabilities are prevalent with an average of 2.8 inter-procedural layers;and (ii) function-level vulnerability detectors are much less effective in detecting to-be-patched functions of inter-procedural vulnerabilities than detecting their counterparts of intra-procedural vulnerabilities. Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

PsFuture: A Pseudo-Future-based Zero-Shot Adaptive Policy for Simultaneous Machine Translation

arXiv

引用

arXiv 2024年

作者： Zhao, Libo Li, Jing Zeng, Ziqian Shien-Ming Wu School of Intelligent Engineering South China University of Technology China Department of Computing Hong Kong Polytechnic University Hong Kong Research Centre for Data Science & Artificial Intelligence Hong Kong Polytechnic University Hong Kong

Simultaneous Machine Translation (SiMT) requires target tokens to be generated in real-time as streaming source tokens are consumed. Traditional approaches to SiMT typically require sophisticated architectures and extensive parameter configurations for training adaptive read/write policies, which in turn demand considerable computational power and memory. We propose PsFuture, the first zero-shot adaptive read/write policy for SiMT, enabling the translation model to independently determine read/write actions without the necessity for additional training. Furthermore, we introduce a novel training strategy, Prefix-to-Full (P2F), specifically tailored to adjust offline translation models for SiMT applications, exploiting the advantages of the bidirectional attention mechanism inherent in offline models. Experiments across multiple benchmarks demonstrate that our zero-shot policy attains performance on par with strong baselines and the P2F method can further enhance performance, achieving an outstanding trade-off between translation quality and latency.1 Copyright © 2024, The Authors. All rights reserved.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

Cognitive Farming in Agriculture: Deploying CNN-RF for Maize Disease Precision Diagnostics

Cognitive Farming in Agriculture: Deploying CNN-RF for Maize...

引用

Contemporary computing and Communications (InC4), IEEE International Conference on

作者： S. Nisha Chandran Ashish Garg Dheeraj Namdev Vinay Kukreja Shiva Mehta School of Computing Graphic Era Hill University Dehradun Uttarakhand India Computer Science and Engineering Graphic Era Deemed to be University Dehradun Uttarakhand India Artificial Intelligence & Data Science IIMT College of Engineering Greater Noida Uttar Pradesh India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

ISBN: (数字)9798350383652

ISBN: (纸本)9798350383669

A hybrid approach integrating both CNN and RF is investigated in this research study of the Survey regarding the classification of maize leaf diseases with the help of CNN and RF. Our research carefully contrasts five created disease severities as a reported diagnostic tool for agriculturalists. The high accuracy of the model was extensively validated by applying various performance metrics with excellent precision of the different classes ranging from 95.90% to 98.47% for recall ranged between 95.01% to 99.21%, and F1- scores ranged between 96.55% to 98.4. The model achieved a general accuracy of 97.42851 %. We employed various averaging approaches to generalize the performance results across varying illness levels. A macro average yielded an accuracy of 97.37%, recall of 97.48%, and F1-score of 97.42%, implying similarity of performance across classes. Considering class imbalance, the weighted average was accurate at 97.44%, recalled at 97.43%, and the F1-score was similar at 97.43%. The micro average, as the aggregation of results across classes, was remarkably stable at 97.43 %, representing the performance of the model well and especially favoring frequent courses. Early identification and classification of diseases affecting maize leaves significantly contributed to precision agriculture, and this paper presents a reliable and efficient method for a timely diagnosis. It shows the stable performance of the CNN-RF model because many statistical measures are indicated. This implies that it possesses reasonable practicality in agricultural applications that highly support pest control and increase crop yields.

关键词： Radio frequency Surveys Precision agriculture Solid modeling Accuracy Computational modeling Solids

来源：评论

学校读者我要写书评

暂无评论

Curvature Graph Generative Adversarial Networks

arXiv

引用

arXiv 2022年

作者： Li, Jianxin Fu, Xingcheng Sun, Qingyun Ji, Cheng Tan, Jiajun Wu, Jia Peng, Hao Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China School of Computing Macquarie University Sydney Australia

Generative adversarial network (GAN) is widely used for generalized and robust learning on graph data. However, for non-Euclidean graph data, the existing GAN-based graph representation methods generate negative samples by random walk or traverse in discrete space, leading to the information loss of topological properties (e.g. hierarchy and circularity). Moreover, due to the topological heterogeneity (i.e., different densities across the graph structure) of graph data, they suffer from serious topological distortion problems. In this paper, we proposed a novel Curvature Graph Generative Adversarial Networks method, named CurvGAN, which is the first GAN-based graph representation method in the Riemannian geometric manifold. To better preserve the topological properties, we approximate the discrete structure as a continuous Riemannian geometric manifold and generate negative samples efficiently from the wrapped normal distribution. To deal with the topological heterogeneity, we leverage the Ricci curvature for local structures with different topological properties, obtaining to low-distortion representations. Extensive experiments show that CurvGAN consistently and significantly outperforms the state-of-the-art methods across multiple tasks and shows superior robustness and generalization. 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

Generalization-Enhanced Code Vulnerability Detection via Multi-Task Instruction Fine-Tuning

arXiv

引用

arXiv 2024年

作者： Du, Xiaohu Wen, Ming Zhu, Jiahao Xie, Zifan Ji, Bin Liu, Huijun Shi, Xuanhua Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China College of Computer National University of Defense Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab HUST Wuhan430074 China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security HUST Wuhan430074 China JinYinHu Laboratory Wuhan430077 China Cluster and Grid Computing Lab HUST Wuhan430074 China

Code Pre-trained Models (CodePTMs) based vulnerability detection have achieved promising results over recent years. However, these models struggle to generalize as they typically learn superficial mapping from source code to labels instead of understanding the root causes of code vulnerabilities, resulting in poor performance in real-world scenarios beyond the training instances. To tackle this challenge, we introduce VulLLM, a novel framework that integrates multi-task learning with Large Language Models (LLMs) to effectively mine deep-seated vulnerability features. Specifically, we construct two auxiliary tasks beyond the vulnerability detection task. First, we utilize the vulnerability patches to construct a vulnerability localization task. Second, based on the vulnerability features extracted from patches, we leverage GPT-4 to construct a vulnerability interpretation task. VulLLM innovatively augments vulnerability classification by leveraging generative LLMs to understand complex vulnerability patterns, thus compelling the model to capture the root causes of vulnerabilities rather than overfitting to spurious features of a single task. The experiments conducted on six large datasets demonstrate that VulLLM surpasses seven state-of-the-art models in terms of effectiveness, generalization, and robustness. © 2024, CC BY.

关键词： Large datasets

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：