检索结果-内蒙古大学图书馆

arXiv 2023年

作者： He, Junwei Xu, Qianqian Jiang, Yangbangyan Wang, Zitai Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

Graph anomaly detection is crucial for identifying nodes that deviate from regular behavior within graphs, benefiting various domains such as fraud detection and social network. Although existing reconstruction-based methods have achieved considerable success, they may face the Anomaly Overfitting and Homophily Trap problems caused by the abnormal patterns in the graph, breaking the assumption that normal nodes are often better reconstructed than abnormal ones. Our observations indicate that models trained on graphs with fewer anomalies exhibit higher detection performance. Based on this insight, we introduce a novel two-stage framework called Anomaly-Denoised Autoencoders for Graph Anomaly Detection (ADA-GAD). In the first stage, we design a learning-free anomaly-denoised augmentation method to generate graphs with reduced anomaly levels. We pretrain graph autoencoders on these augmented graphs at multiple levels, which enables the graph autoencoders to capture normal patterns. In the next stage, the decoders are retrained for detection on the original graph, benefiting from the multi-level representations learned in the previous stage. Meanwhile, we propose the node anomaly distribution regularization to further alleviate Anomaly Overfitting. We validate the effectiveness of our approach through extensive experiments on both synthetic and real-world datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Impact of China Railway Express on Urban Exports: Evidence from Prefectural-Level City Economic data

引用

Procedia Computer Science 2022年 214卷 1222-1227页

作者： Bochao Yan Xin Tian Shiyong Deng Junfeng Wu Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China China Railway Fifth Survey and Design Institute Group Co. Ltd. Beijing 102600 China Shanghai WinJoin Information Technology Co. Ltd. Shanghai 200126 China

As a key project of infrastructure connectivity in the “Five-Pronged Approach” of strategic construction “The Belt and Road”, the China Railway Express, has significantly improved the level of trade level in countries along the railway. This study uses an empirical model to correlate the container export data of China Railway Express from June 2020 to June 2021 with the export value and finds that the trade volume of China Railway Express is positively correlated with the export value of cities. The relationship between the operation of the China Railway Express and the export trade of cities that enjoy the rail service is rigorously explained through the actual data of the operation of the China Railway Express provided by the enterprises. The empirical results further prove the positive impact of the China Railway Express on cities that enjoy the rail service.

关键词： The Belt Road China Railway Express Trade

来源：评论

学校读者我要写书评

暂无评论

Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China

Diffusion models are initially designed for image generation. Recent research shows that the internal signals within their backbones, named activations, can also serve as dense features for various discriminative tasks such as semantic segmentation. Given numerous activations, selecting a small yet effective subset poses a fundamental problem. To this end, the early study of this field performs a large-scale quantitative comparison of the discriminative ability of the activations. However, we find that many potential activations have not been evaluated, such as the queries and keys used to compute attention scores. Moreover, recent advancements in diffusion architectures bring many new activations, such as those within embedded ViT modules. Both combined, activation selection remains unresolved but overlooked. To tackle this issue, this paper takes a further step with a much broader range of activations evaluated. Considering the significant increase in activations, a full-scale quantitative comparison is no longer operational. Instead, we seek to understand the properties of these activations, such that the activations that are clearly inferior can be filtered out in advance via simple qualitative evaluation. After careful analysis, we discover three properties universal among diffusion models, enabling this study to go beyond specific models. On top of this, we present effective feature selection solutions for several popular diffusion models. Finally, the experiments across multiple discriminative tasks validate the superiority of our method over the SOTA competitors. Our code is available at this url. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques

arXiv

引用

arXiv 2024年

作者： Meng, Benyuan Xu, Qianqian Wang, Zitai Yang, Zhiyong Cao, Xiaochun Huang, Qingming Institute of Information Engineering CAS China School of Cyber Security University of Chinese Academy of Sciences China Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China Peng Cheng Laboratory China School of Computer Science and Tech. University of Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management CAS China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China

Diffusion models are powerful generative models, and this capability can also be applied to discrimination. The inner activations of a pre-trained diffusion model can serve as features for discriminative tasks, namely, diffusion feature. We discover that diffusion feature has been hindered by a hidden yet universal phenomenon that we call content shift. To be specific, there are content differences between features and the input image, such as the exact shape of a certain object. We locate the cause of content shift as one inherent characteristic of diffusion models, which suggests the broad existence of this phenomenon in diffusion feature. Further empirical study also indicates that its negative impact is not negligible even when content shift is not visually perceivable. Hence, we propose to suppress content shift to enhance the overall quality of diffusion features. Specifically, content shift is related to the information drift during the process of recovering an image from the noisy input, pointing out the possibility of turning off-the-shelf generation techniques into tools for content shift suppression. We further propose a practical guideline named GATE to efficiently evaluate the potential benefit of a technique and provide an implementation of our methodology. Despite the simplicity, the proposed approach has achieved superior results on various tasks and datasets, validating its potential as a generic booster for diffusion features. Our code is available at this url. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pyramid scheme model for consumption rebate frauds

引用

Chinese Physics B 2019年第7期28卷 549-556页

作者： Yong Shi Bo Li Wen Long School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China

There are various types of pyramid schemes that have inflicted or are inflicting losses on many people in the *** propose a pyramid scheme model which has the principal characters of many pyramid schemes that have appeared in recent years: promising high returns, rewarding the participants for recruiting the next generation of participants, and the organizer takes all of the money away when they find that the money from the new participants is not enough to pay the previous participants interest and *** assume that the pyramid scheme is carried out in the tree network, Erd?s–Réney(ER) random network, Strogatz–Watts(SW) small-world network, or Barabasi–Albert(BA) scale-free *** then give the analytical results of the generations that the pyramid scheme can last in these *** also use our model to analyze a pyramid scheme in the real world and we find that the connections between participants in the pyramid scheme may constitute a SW small-world network.

关键词： pyramid scheme complex networks small-world networks

来源：评论

学校读者我要写书评

暂无评论

A brief overview of kernel methods with prior information

引用

Procedia Computer Science 2022年 199卷 269-275页

作者： Saiji Fu Shiding Sun Xinfeng Wang Dalian Liu School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China Institute of Mathematics and Physics Beijing Union University Beijing 100101 China Institute of Fundamental and Interdisciplinary Sciences Beijing Union University Beijing 100101 China

With the progress of human society and the development of computer technology, more and more experience has been accu¬mulated, which can serve as prior information in model training. With the assistance of prior information, the performance of some machine learning algorithms has been significantly improved. In this article, we mainly discussed four types of prior information, namely knowledge sets, fuzzy sets, universum data, and privilege information. Specifically, (1) the knowledge sets are constraints composed of domain experience; (2) the fuzzy sets provide the importance of each instance through the fuzzy membership function; (3) the universum data belongs to none of the target classes, but reflects the domain information related to the field of interest; (4) the privileged information can provide more relevant information about training examples, but is not available during the testing phase. In order to illustrate how the prior information is integrated into the kernel methods, the cor¬responding representative models are reviewed in detail, including knowledge-based support vector machine(KSVM), fuzzy support vector machine(FSVM), universum support vector machine(USVM) and privileged support vector machine(SVM+). In addition, this article briefly introduced the most related and advanced research, including the deep learning extensions with prior information. Finally, the current challenge and the future trends of incorporating prior information into machine learning are discussed.

关键词： prior information kernel methods support vector machine deep learning

来源：评论

学校读者我要写书评

暂无评论

A knowledge graph constructed for job-related crimes

引用

Procedia Computer Science 2022年 199卷 540-547页

作者： Yong Shi Wenlu An Jiayu Xue Yi Qu School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 CHINA Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 CHINA Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 CHINA College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA People’s Procuratorate of Shanghai Pudong New District Shanghai 200135 CHINA School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 100190 China

Since the 18th National Congress, the Party Central Committee has greatly enhanced its efforts to "fight corruption and advocate honesty". While achieving excellent results, the rising number of crime cases has also brought great challenges to the work of the prosecution organs. At the same time, the traditional relational database has become more and more disadvantageous in dealing with large-scale, unstructured and complex dynamic data, and can no longer meet the actual needs. In order to further improve the efficiency and quality of prosecutors’ work, alleviate the problem of "too many cases and too few people", and promote the construction of "smart prosecution", this paper uses knowledge extraction and other methods to identify the key entities and relationships in the job-related crimes indictments of the Shanghai Pudong New District Procuratorate. Then using Neo4j graph database to store the extracted information and build a knowledge graph for job-related crime cases, which realizes the visualization and deep mining of job-related crime, providing a new way and tool for prosecution work as well as prosecution personnel to analyze and handle job-related crime cases.

关键词： big data in prosecution knowledge graph job-related crimes Neo4j

来源：评论

学校读者我要写书评

暂无评论

Price change prediction of ultra high frequency financial data based on temporal convolutional network

arXiv

引用

arXiv 2021年

作者： Dai, Wei An, Yuan Long, Wen School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

Through in-depth analysis of ultra high frequency (UHF) stock price change data, more reasonable discrete dynamic distribution models are constructed in this paper. Firstly, we classify the price changes into several categories. Then, temporal convolutional network (TCN) is utilized to predict the conditional probability for each category. Furthermore, attention mechanism is added into the TCN architecture to model the time-varying distribution for stock price change data. Empirical research on constituent stocks of Chinese Shenzhen Stock Exchange 100 Index (SZSE 100) found that the TCN framework model and the TCN (attention) framework have a better overall performance than GARCH family models and the long short-term memory (LSTM) framework model for the description of the dynamic process of the UHF stock price change sequence. In addition, the scale of the dataset reached nearly 10 million, to the best of our knowledge, there has been no previous attempt to apply TCN to such a large-scale UHF transaction price dataset in Chinese stock market. Copyright © 2021, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and Deep Learning Methods used in Safety management of Nuclear Power Plants: A Survey

Machine Learning and Deep Learning Methods used in Safety Ma...

引用

IEEE International Conference on data mining Workshops (ICDM Workshops)

作者： Yong Shi Xiaodong Xue Yi Qu Jiayu Xue Linzi Zhang Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China College of Information Science and Technology University of Nebraska at Omaha Omaha USA School of Economics and Management University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665424288

The nuclear power industry is currently a strategic sector in the national economy, along with nuclear energy being considered to be an essential source of national power supply and security. Under such circumstances, nuclear power plants (NPPs) have been constructed globally in recent decades, providing stable and large amounts of electricity to many countries and regions for quite a long time. However, due to the specialty of NPPs, safety management is always the top priority in their daily operations, like fault diagnosis and monitoring. At the same time, with the great development of artificial intelligence, machine learning and deep learning methods have been infiltrating lots of disciplines and resulting in more intelligent transformations in real industries. By the strength of better performance, machine learning and deep learning models have been introduced into research and practice of safety management in NPPs, not only producing more academic papers but also ensuring stable and safe operations of NPPs. Focusing on the safety management of NPPs, this article starts with the common trend of data analytics, also the evolving process of algorithms applied in academia and real practice, which is from model-driven methods to data-driven approaches. Then detailed applications of conventional machine learning, advanced deep learning and other related intelligent approaches used in the safety management of NPPs are comprehensively categorized and reviewed. Further, we make necessary summaries and discussions, proposing new ideas and perspectives to better promote the theoretical and practical development of safety management in NPPs.

关键词： Deep learning Machine learning algorithms Power supplies Safety management Focusing Market research Power industry

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Crowd Counting Learns from Sorting Rather Than Locations 1

引用

16th European Conference on Computer Vision, ECCV 2020

作者： Yang, Yifan Li, Guorong Wu, Zhe Su, Li Huang, Qingming Sebe, Nicu School of Computer Science and Technology UCAS Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Key Lab of Intelligent Information Processing ICT CAS Beijing China University of Trento Trento Italy

ISBN: (数字)9783030585983

ISBN: (纸本)9783030585976

In crowd counting datasets, the location labels are costly, yet, they are not taken into the evaluation metrics. Besides, existing multi-task approaches employ high-level tasks to improve counting accuracy. This research tendency increases the demand for more annotations. In this paper, we propose a weakly-supervised counting network, which directly regresses the crowd numbers without the location supervision. Moreover, we train the network to count by exploiting the relationship among the images. We propose a soft-label sorting network along with the counting network, which sorts the given images by their crowd numbers. The sorting network drives the shared backbone CNN model to obtain density-sensitive ability explicitly. Therefore, the proposed method improves the counting accuracy by utilizing the information hidden in crowd numbers, rather than learning from extra labels, such as locations and perspectives. We evaluate our proposed method on three crowd counting datasets, and the performance of our method plays favorably against the fully supervised state-of-the-art approaches. © 2020, Springer Nature Switzerland AG.

关键词： Location

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：