检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Han, Boyu Xu, Qianqian Yang, Zhiyong Bao, Shilong Wen, Peisong Jiang, Yangbangyan Huang, Qingming Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS China School of Computer Science and Tech. University of Chinese Academy of Sciences China Peng Cheng Laboratory China Key Laboratory of Big Data Mining and Knowledge Management CAS China

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm’s generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg. © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on regularization strategies in machine learning

引用

INFORMATION FUSION 2022年 80卷 146-166页

作者： Tian, Yingjie Zhang, Yuqi Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

In machine learning, the model is not as complicated as possible. Good generalization ability means that the model not only performs well on the training data set, but also can make good prediction on new data. Regularization imposes a penalty on model's complexity or smoothness, allowing for good generalization to unseen data even when training on a finite training set or with an inadequate iteration. Deep learning has developed rapidly in recent years. Then the regularization has a broader definition: regularization is a technology aimed at improving the generalization ability of a model. This paper gave a comprehensive study and a state-of-the-art review of the regularization strategies in machine learning. Then the characteristics and comparisons of regularizations were presented. In addition, it discussed how to choose a regularization for the specific task. For specific tasks, it is necessary for regularization technology to have good mathematical characteristics. Meanwhile, new regularization techniques can be constructed by extending and combining existing regularization techniques. Finally, it concluded current opportunities and challenges of regularization technologies, as well as many open concerns and research trends.

关键词： Overfitting Generalization Regularization Machine learning

来源：评论

学校读者我要写书评

暂无评论

Literature Review and Practice Comparison of Technology Foresight

引用

Procedia Computer Science 2022年 199卷 837-844页

作者： Zhao Minghui Ye Hanrui Peng Yao Zhang Lingling 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

With continuous breakthrough of key technologies, common technologies, emerging technologies, cross technologies, and subversive technologies, which have brought profound changes to politics, economy, society, culture, and environment. Under above-mentioned background, further exert the guiding role of technology foresight in technology planning formulation, further study the supporting role of technology foresight in emerging technology management, which is important for academic research, enterprise practice and government decision-making. This article can be divided into two parts, the literature review part mainly includes published articles, keyword network, citation network, which describes the historical context, current status, future trends, limitations and improvement directions of related research in detail. The practice comparison part mainly includes targets and experts, methods and processes, technologies and fields, which is also a feasible perspective for results evaluating.

关键词： Technology Foresight Literature Review Practice Comparison

来源：评论

学校读者我要写书评

暂无评论

Method for Improving the Performance of Technical Analysis Indicators By Neural Network Models

引用

COMPUTATIONAL ECONOMICS 2022年第3期59卷 1027-1068页

作者： Shi, Yong Li, Bo Long, Wen Dai, Wei Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China Southwest Minzu Univ Coll Elect & Informat Engn Chengdu 610041 Peoples R China

Technical analysis indicators are widely used in the field of quantitative investment, and they are usually utilized to assist in the search for profitable buy and sell points. In order to make better use of technical indicators, a method of trying to improve the performance of technical indicators by using neural network models is proposed in this work. The method tries to utilize neural network models to learn the possible patterns or features of price and volume before the profitable buy or sell points indicated by technical indicators. In modeling, a certain length of historical market data before the buy and sell points indicated by technical indicators is taken as model inputs, and whether or not can these buy and sell points meet certain profit standard is taken as labels. We validate our method on stock indexes, stocks and futures, and the results show that our method can improve the performance of several simple but common strategies based on technical analysis indicators.

关键词： Technical analysis indicators Neural network models Quantitative investment

来源：评论

学校读者我要写书评

暂无评论

Literature Review and Practice Comparison of Technology Foresight 8

Literature Review and Practice Comparison of Technology Fore...

引用

8th International Conference on Information Technology and Quantitative management, ITQM 2020 and 2021

作者： Minghui, Zhao Hanrui, Ye Yao, Peng Lingling, Zhang School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Cost-sensitive learning with modified Stein loss function

引用

NEUROCOMPUTING 2023年第1期525卷 57-75页

作者： Fu, Saiji Tian, Yingjie Tang, Jingjing Liu, Xiaohui Beijing Univ Posts & Telecommun Sch Econ & Management Beijing 100876 Peoples R China Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China MOE Social Sci Lab Digital Econ Forecasts & Policy Beijing 100190 Peoples R China Southwestern Univ Finance & Econ Fac Business Adm Sch Business Adm Sichuan 611130 Peoples R China Brunel Univ London Dept Comp Sci London UB8 3PH England

Cost-sensitive learning (CSL), which has gained widespread attention in class imbalance learning (CIL), can be implemented either by tuning penalty parameters or by designing new loss functions. In this paper, we propose a cost-sensitive learning method with a modified Stein loss function (CSMS) and a robust CSMS (RCSMS). Specifically, CSMS is flexible, as it realizes CSL from above two aspects simultane-ously. In contrast, RCSMS merely achieves CSL by tuning penalty parameters, but the adopted loss func-tion makes it insensitive to noise. To our best knowledge, it is the first time for Stein loss function derived from statistics to be applied in machine learning, which not only offers two alternative class imbalance solutions but also provides a novel idea for the design of loss functions in CIL. The mini-batch stochastic sub-gradient descent (MBGD) approach is employed to optimize CSMS and RCSMS. Meanwhile, the Rademacher complexity is used to analyze their generalization error bounds. Extensive experiments pro-foundly confirm the superiority of both models over benchmarks.(c) 2023 Elsevier B.V. All rights reserved.

关键词： Class imbalance learning Cost-sensitive learning Stein loss function Penalty parameter Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Movie Recommendation Algorithm Based on Sentiment Analysis and LDA

引用

Procedia Computer Science 2022年 199卷 871-878页

作者： Yilin Zhang Lingling Zhang 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

Traditional recommendation algorithms have problems such as data sparseness and not paying attention to the diversity of recommendation results. In this paper, we use LDA to extract topics of comments about movies, and identify the emotional tendencies related to topics. As a result, we enrich user interest model and product feature model based on emotional tendencies to improve content-based recommendation algorithms. Most of prior work on applying sentiment classification to recommendation systems only consider the use of sentiment dictionaries to judge polarity, and adopt pattern matching methods to identify features. This paper uses BERT to train sentiment classification models and uses LDA to extract topics. The algorithm is run on the movie review database crawled from Douban, and the experimental result showed that the diversity of recommendation lists had been significantly improved.

关键词： Sentiment Analysis Topic Extraction Content-based Recommendation Movie Reviews

来源：评论

学校读者我要写书评

暂无评论

ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection 38

ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Det...

引用

38th AAAI Conference on Artificial Intelligence (AAAI) / 36th Conference on Innovative Applications of Artificial Intelligence / 14th Symposium on Educational Advances in Artificial Intelligence

作者： He, Junwei Xu, Qianqian Jiang, Yangbangyan Wang, Zitai Huang, Qingming Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing Peoples R China Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

ISBN: (纸本)1577358872

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.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Digital economy, technical change and total factor productivity: Empirical evidence from high-tech industry in China

引用

TELECOMMUNICATIONS POLICY 2024年第9期48卷

作者： Zhang, Linyan Hu, Chunyu Guo, Chuanyin Wang, Jianguo Beijing Informat Sci & Technol Univ Sch Econ & Management Beijing 100192 Peoples R China Res Ctr Knowledge Management Beijing 100192 Peoples R China Beijing Key Lab Green Dev Decis Based Big Data Beijing 100192 Peoples R China

This study uses the Hicks-Moorsteen index method to examine the impact mechanism of the digital economy on the total factor productivity and its decomposition efficiencies of the hightech industry in China. The results show that the total factor productivity of the high-tech industry in the research and development phase is significantly and positively influenced by the primary phase of digital economy development. Digital economy development has a positive impact on technical change, according to the specific path analysis, which has an inverted Ushaped nonlinear characteristic. With a U-shaped nonlinear characteristic, it has a significant and persistent negative impact on efficiency changes, where the positive impact of technological spillovers on the digital economy outweighs the negative impact of technological shocks. The threshold effect test shows that the best condition for promoting total factor productivity and its decomposition efficiency in the R&D stage of high-tech industry was achieved when the digital economy composite index was between 2.611 and 2.747.

关键词： Digital economy Total factor productivity (TFP) Hicks-moorsteen index Nonlinear impact Threshold effect High-tech industry

来源：评论

学校读者我要写书评

暂无评论

Rethinking Collaborative Metric Learning: Toward an Efficient Alternative Without Negative Sampling

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023年第1期45卷 1017-1035页

作者： Bao, Shilong Xu, Qianqian Yang, Zhiyong Cao, Xiaochun Huang, Qingming Chinese Acad Sci Inst Informat Engn State Key Lab Informat Secur SKLOIS Beijing 100093 Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing 100049 Peoples R China Chinese Acad Sci Inst Comp Technol Key Lab Intelligent Informat Proc Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management BDKM Sch Comp Sci & Technol Beijing 101408 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China

The recently proposed Collaborative Metric Learning (CML) paradigm has aroused wide interest in the area of recommendation systems (RS) owing to its simplicity and effectiveness. Typically, the existing literature of CML depends largely on the negative sampling strategy to alleviate the time-consuming burden of pairwise computation. However, in this work, by taking a theoretical analysis, we find that negative sampling would lead to a biased estimation of the generalization error. Specifically, we show that the sampling-based CML would introduce a bias term in the generalization bound, which is quantified by the per-user Total Variance (TV) between the distribution induced by negative sampling and the ground truth distribution. This suggests that optimizing the sampling-based CML loss function does not ensure a small generalization error even with sufficiently large training data. Moreover, we show that the bias term will vanish without the negative sampling strategy. Motivated by this, we propose an efficient alternative without negative sampling for CML named Sampling-Free Collaborative Metric Learning (SFCML), to get rid of the sampling bias in a practical sense. Finally, comprehensive experiments over seven benchmark datasets speak to the supriority of the proposed algorithm.

关键词： Recommendation system collaborative metric learning negative sampling machine learning

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：