检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Qian, Yaguan Wang, Yuqi Wang, Bin Gu, Zhaoquan Guo, Yuhan Swaileh, Wassim School of Big Data Science Zhejiang University of Science and Technology Hangzhou China Zhejiang Key Laboratory of Multi-dimensional Perception Technology Application and Cybersecurity Hikvision Digital Technology Co. Ltd Hangzhou China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China ETIS Research Laboratory CY Cergy Paris University Paris France

—Recent studies show deep neural networks (DNNs) are extremely vulnerable to the elaborately designed adversarial examples. Adversarial learning with those adversarial examples has been proved as one of the most effective methods to defend against such an attack. At present, most existing adversarial examples generation methods are based on first-order gradients, which can hardly further improve models’ robustness, especially when facing second-order adversarial attacks. Compared with first-order gradients, second-order gradients provide a more accurate approximation of the loss landscape with respect to natural examples. Inspired by this, our work crafts second-order adversarial examples and uses them to train DNNs. Nevertheless, second-order optimization involves time-consuming calculation for Hessian-inverse. We propose an approximation method through transforming the problem into an optimization in the Krylov subspace, which remarkably reduce the computational complexity to speed up the training procedure. Extensive experiments conducted on the MINIST and CIFAR-10 datasets show that our adversarial learning with second-order adversarial examples outperforms other fisrt-order methods, which can improve the model robustness against a wide range of attacks. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Constraint-Based Model for the Frequent Itemset Hiding Problem 8th

A Constraint-Based Model for the Frequent Itemset Hiding Pro...

引用

8th e-Democracy International Conference on Safeguarding Democracy and Human Rights in the Digital Age, e-Democracy 2019

作者： Verykios, Vassilios S. Stavropoulos, Elias C. Zorkadis, Vasilis Elmagarmid, Ahmed K. Big Data Analytics and Anonymization Laboratory School of Science and Technology Hellenic Open University Patras Greece Educational Content Methodology and Technology Laboratory Hellenic Open University Patras Greece Hellenic Data Protection Authority Athens Greece Qatar Computing Research Institute HBKU Doha Qatar

ISBN: (纸本)9783030375447

This paper introduces a novel constraint-based hiding model to drastically reduce the preprocessing overhead that is incurred by border-based techniques in the hiding of sensitive frequent itemsets. The proposed model is solved by an efficient constraint-based mining algorithm that pushes a conjunction of antimonotone constraints into an Apriori-like algorithm, for inducing the support theory of non-sensitive frequent itemsets along with its negative border. The patterns induced by the constraint-based mining algorithm can be used in border-based hiding algorithms to construct a sanitized version of the original database, where the sensitive knowledge is concealed. The efficiency of the constraint-based mining algorithm is evaluated on real and synthetic datasets. © Springer Nature Switzerland AG 2020.

关键词： Linear programming

来源：评论

学校读者我要写书评

暂无评论

RAGRAPH: a general retrieval-augmented graph learning framework 24

RAGRAPH: a general retrieval-augmented graph learning framew...

引用

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

作者： Xinke Jiang Rihong Qiu Yongxin Xu Wentao Zhang Yichen Zhu Ruizhe Zhang Yuchen Fang Xu Chu Junfeng Zhao Yasha Wang Key Laboratory of High Confidence Software Technologies (Peking University) School of Computer Science Peking University China University of Electronic Science and Technology of China Key Laboratory of High Confidence Software Technologies (Peking University) School of Computer Science Peking University China and Center on Frontiers of Computing Studies Peking University Beijing China and Peking University Information Technology Institute Tianjin Binhai China Key Laboratory of High Confidence Software Technologies (Peking University) School of Computer Science Peking University China and Big Data Technology Research Center Nanhu Laboratory Jiaxing China Key Laboratory of High Confidence Software Technologies (Peking University) School of Computer Science Peking University China and Peking University Information Technology Institute Tianjin Binhai China

ISBN: (纸本)9798331314385

Graph Neural Networks (GNNs) have become essential in interpreting relational data across various domains, yet, they often struggle to generalize to unseen graph data that differs markedly from training instances. In this paper, we introduce a novel framework called General Retrieval-Augmented Graph Learning (RAGRAPH), which brings external graph data into the general graph foundation model to improve model generalization on unseen scenarios. On the top of our framework is a toy graph vector library that we established, which captures key attributes, such as features and task-specific label information. During inference, the RAGRAPH adeptly retrieves similar toy graphs based on key similarities in downstream tasks, integrating the retrieved data to enrich the learning context via the message-passing prompting mechanism. Our extensive experimental evaluations demonstrate that RAGRAPH significantly outperforms state-of-the-art graph learning methods in multiple tasks such as node classification, link prediction, and graph classification across both dynamic and static datasets. Furthermore, extensive testing confirms that RAGRAPH consistently maintains high performance without the need for task-specific fine-tuning, highlighting its adaptability, robustness, and broad applicability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Active Legibility in Multiagent Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Liu, Yanyu Pan, Yinghui Zeng, Yifeng Ma, Biyang Prashant, Doshi School of Automation Central South University No.605 South Lushan Road Hunan Changsha410083 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen China Department of Computer and Information Sciences Northumbria University Newcastle United Kingdom School of Computer Science Minnan Normal University Fujian Zhangzhou China Department of Computer Science University of Georgia AthensGA United States

A multiagent sequential decision problem has been seen in many critical applications including urban transportation, autonomous driving cars, military operations, etc. Its widely known solution, namely multiagent reinforcement learning, has evolved tremendously in recent years. Among them, the solution paradigm of modeling other agents attracts our interest, which is different from traditional value decomposition or communication mechanisms. It enables agents to understand and anticipate others’ behaviors and facilitates their collaboration. Inspired by recent research on the legibility that allows agents to reveal their intentions through their behavior, we propose a multiagent active legibility framework to improve their performance. The legibility-oriented framework allows agents to conduct legible actions so as to help others optimise their behaviors. In addition, we design a series of problem domains that emulate a common scenario and best characterize the legibility in multiagent reinforcement learning. The experimental results demonstrate that the new framework is more efficient and costs less training time compared to several multiagent reinforcement learning algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Short-Term Electric Load Forecasting Via State-State Approach with a Mixture of Long-Lag Vector Autoregressive Models

SSRN

引用

SSRN 2023年

作者： Jeong, Dongyeon Park, Chiwoo Ko, Young Myoung Samsung Electronics 56 Seongchon-gil Seocho-gu Seoul06765 Korea Republic of Department of Industrial and Management Engineering Pohang University of Science and Technology Gyeongbuk Pohang37673 Korea Republic of Open Innovation Big Data Center Pohang University of Science and Technology Gyeongbuk Pohang37673 Korea Republic of Graduate School of Artificial Intelligence Pohang University of Science and Technology Gyeongbuk Pohang37673 Korea Republic of Department of Industrial and Manufacturing Engineering Florida State University TallahasseeFL32306 United States

This paper proposes a novel day-ahead electric load forecasting model for buildings and regions. We explore the problem that the daily load curves of electric load data in buildings and regions have periodicity and follow some patterns. We use long-lag terms of historical load data to capture periodicity and clustering to figure out daily load curve patterns. We propose a forecast model called a state-space model with a mixture of long-lag vector autoregressive models (SSM-MLVAR), which combines a state-space model and long-lag vector autoregressive models into a single model. The proposed model ensures feasibility by reducing the number of parameters of the long-lag vector autoregressive model. The state-space model alleviates forecasting errors that cannot be fine-tuned with the vector autoregressive model. With electric load data from a building and 10 regions, we compare the proposed model with existing forecasting methods such as persistence, multiple-output support vector machine (M-SVM), cluster model (CM), logistic mixture vector autoregressive model (LMVAR), Bayesian mixture density network (BayMDN), and variational mode decomposition with multiple wavelet decomposition network (VMD-mWDN). It turns out that the proposed model achieves significantly higher prediction accuracy than these models on the datasets. © 2023, The Authors. All rights reserved.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Controlled-source electromagnetic noise attenuation via a deep convolutional neural network and high-quality sounding curve screening mechanism

引用

Geophysics 2025年第3期90卷 WA125-WA140页

作者： Liu, Yecheng Li, Diquan Li, Jin Zhang, Xian Central South University Monitoring Ministry of Education Key Laboratory of Metallogenic Prediction of Nonferrous Metals and Geological Environment Changsha China Hunan Provincial Key Laboratory of Non-ferrous Resources and Geological Hazard Detection Changsha China Central South University School of Geoscience and Info-physics Changsha China Hunan Normal University College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Changsha China Hunan University of Finance and Economics School of Information Technology and Management Hunan Provincial Key Laboratory of Finance & Economics Big Data Science and Technology Changsha China

Strong noise is one of the biggest challenges in controlled-source electromagnetic (CSEM) exploration, which severely affects the quality of the recorded signal. We develop a novel and effective CSEM noise attenuation method that integrates a deep convolutional neural network (DCNN) with a high-quality sounding curve screening mechanism. This method first uses a DCNN to learn the large-scale noise characteristics of CSEM measured data and build a DCNN denoising model for attenuating the noise. Because some impulse noise remains after DCNN denoising, the high-quality sounding curve screening mechanism is innovatively applied to optimize the DCNN denoised data. The core of this method is the smoothness value (SV), which quantitatively evaluates the smoothness of the sounding curve (apparent resistivity curve). In effect, the mechanism segments the overall DCNN denoised data and calculates the corresponding sounding curve and its SV for each segment. The highest-quality sounding curve can be screened out by comparing the SVs of all curves as well as obtaining the highest-quality data segment present in the overall DCNN denoised data. Finally, our method is validated with synthetic and field data, demonstrating its feasibility and effectiveness in attenuating large-scale CSEM noise. The quality of CSEM data, which is heavily affected by noise, is significantly improved after processing by our method. © 2025 Society of Exploration Geophysicists. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning Representations from Local to Global for Fine-grained Patient Similarity Measuring in Intensive Care Unit

Learning Representations from Local to Global for Fine-grain...

引用

IEEE International Conference on data Mining (ICDM)

作者： Xianli Zhang Buyue Qian Yang Li Zeyu Gao Chong Guan Renzhen Wang Yefeng Zheng Hansen Zheng Chen Li School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Beijing Chaoyang Hospital Capital Medical University Tencent Shenzhen Guandong China School of Mathematics and Statistics Xi’an Shaanxi China

Patient similarity measurement is an essential step in discovering clinically meaningful subgroups and building case retrieval systems. Most existing studies implement this procedure using similarity measurement algorithms on the multivariate clinical time-series (input space) or the low-dimensional patient representation (representation space) learned by a representation learning model. However, they either suffer from the adverse effects of irrelevant variables in the data or fail to assess the fine-grained similarity underneath the disease progress. In this paper, we propose a method to measure more fine-grained patient similarity in the state space, where each patient is represented by a series of state representations that reveal the dynamic health status. We discuss three desiderata, including stability, personality, and interpretability, for the state representations, and on this basis, develop a supervised predictive model that learns good state representations for identifying similar patients and predicting patient outcomes. Experimental results on the publicly available dataset MIMIC-III show that our method offers a promising direction for precisely identifying similar patients at the state trajectory level, as well as accurately predicting outcomes.

关键词： Training Representation learning Measurement units Precision medicine MIMICs Predictive models Extraterrestrial measurements

来源：评论

学校读者我要写书评

暂无评论

Tumor State-Space Network for High and Low Grade Glioma Classification

Tumor State-Space Network for High and Low Grade Glioma Clas...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Qijian Chen Lihui Wang Zeyu Deng Li Wang Chen Ye YueMin Zhu Engineering Research Center of Text Computing Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China INSA Lyon CNRS Inserm IRP Metislab CREATIS UMR5220 U1206 University Lyon Lyon France

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Accurately predicting the grade of gliomas is crucial for choosing right treatment plans. While current methods using radiomics and deep learning can predict glioma grades effectively using magnetic resonance imaging (MRI), they overlook dynamic changes in the tumor and its neighboring areas. To address this issue, we propose a tumor state-space network (TSSNet), which fully exploits changes in the tumor region and its surroundings through dynamical updating strategy. The experimental results demonstrated that TSSNet achieves 90.32% accuracy and 93.55% area under the curve (AUC) for the prediction of high-grade and low-grade gliomas, respectively, which are 2.4% and 2.5% higher than the best state-of-the-art deep learning models. Moreover, the proposed state-space module can effectively enhance prediction performance, which is advantageous for personalized glioma treatment.

关键词： Deep learning Accuracy Magnetic resonance imaging Signal processing Predictive models Tumors Radiomics

来源：评论

学校读者我要写书评

暂无评论

Informative dropout for robust representation learning: A shape-bias perspective 37

Informative dropout for robust representation learning: A sh...

引用

37th International Conference on Machine Learning, ICML 2020

作者： Shi, Baifeng Zhang, Dinghuai Dai, Qi Zhu, Zhanxing Mu, Yadong Wang, Jingdong School of Eecs Peking University China School of Mathematical Sciences Peking University China Microsoft Research Asia Center for Data Science Peking University China Beijing Institute of Big Data Research China Wangxuan Institute of Computer Technology Peking University China

ISBN: (纸本)9781713821120

Convolutional Neural Networks (CNNs) are known to rely more on local texture rather than global shape when making decisions. Recent work also indicates a close relationship between CNN's texture-bias and its robustness against distribution shift, adversarial perturbation, random corruption, etc. In this work, we attempt at improving various kinds of robustness universally by alleviating CNN's texture bias. With inspiration from the human visual system, we propose a light-weight model-agnostic method, namely Informative Dropout (InfoDrop), to improve interpretability and reduce texture bias. Specifically, we discriminate texture from shape based on local self-information in an image, and adopt a Dropout-like algorithm to decorrelate the model output from the local texture. Through extensive experiments, we observe enhanced robustness under various scenarios (domain generalization, few-shot classification, image corruption, and adversarial perturbation). To the best of our knowledge, this work is one of the earliest attempts to improve different kinds of robustness in a unified model, shedding new light on the relationship between shape-bias and robustness, also on new approaches to trustworthy machine learning algorithms. Code is available at https://***/bfshi/InfoDrop. © 2020 37th International Conference on Machine Learning, ICML 2020. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Stability and generalization of kernel clustering: from single kernel to multiple kernel 22

Stability and generalization of kernel clustering: from sing...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Weixuan Liang Xinwang Liu Yong Liu Sihang Zhou Jun-Jie Huang Siwei Wang Jiyuan Liu Yi Zhang En Zhu School of Computer National University of Defense Technology (NUDT) Changsha China Gaoling School of Artificial Intelligence Renmin University of China Beijing China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China College of Intelligence Science and Technology NUDT Changsha China

ISBN: (纸本)9781713871088

Multiple kernel clustering (MKC) is an important research topic that has been widely studied for decades. However, current methods still face two problems: inefficient when handling out-of-sample data points and lack of theoretical study of the stability and generalization of clustering. In this paper, we propose a novel method that can efficiently compute the embedding of out-of-sample data with a solid generalization guarantee. Specifically, we approximate the eigen functions of the integral operator associated with the linear combination of base kernel functions to construct low-dimensional embeddings of out-of-sample points for efficient multiple kernel clustering. In addition, we, for the first time, theoretically study the stability of clustering algorithms and prove that the single-view version of the proposed method has uniform stability as O(Kn-3/2) and establish an upper bound of excess risk as Õ(Kn-3/2 + n-1/2), where K is the cluster number and n is the number of samples. We then extend the theoretical results to multiple kernel scenarios and find that the stability of MKC depends on kernel weights. As an example, we apply our method to a novel MKC algorithm termed SimpleMKKM and derive the upper bound of its excess clustering risk, which is tighter than the current results. Extensive experimental results validate the effectiveness and efficiency of the proposed method.

关键词：

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：