检索结果-内蒙古大学图书馆

TechRxiv 2023年

作者： Mi, Yunlong Liu, Wenqi Shi, Yong The Big Data and Intelligent Decision Making Research Center Central South University Changsha410083 China The Data Science Research Center Kunming University of Science and Technology Kunming650500 China The Faculty of Science Kunming University of Science and Technology Kunming650500 China The School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China The Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

People can often acquire knowledge dynamically and rapidly from different types of data, yet existing incremental learning algorithms are still computationally time consuming and most of stream learning methods are mainly designed for streaming data while ignoring other types of data. Hence, this paper proposes a novel dynamic concept learning (CL) algorithm by imitating human cognitive learning processes from the perspective of brain logical cognition, which is named stream concept-cognitive computing system (streamC3S). For streamC3S, it mainly consists of three aspects: the concept space, CL process, and model update process. Moreover, considering the concept drift frequently occurs in the streaming data over time, an extended version of streamC3S (namely, streamC3SE) is also proposed in this work. Specifically, we first show the related theories for streamC3S and streamC3SE on the basis of the concept space. Then an overall framework and its corresponding algorithm are shown. Finally, experimental results on various types of datasets, including the standard machine learning datasets, streaming datasets, image datasets, and two traffic data streams, validate the effectiveness of our streamC3S and streamC3SE compared to the state-of-the-art incremental learning and stream learning algorithms. © 2023, CC BY.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Overview of Essential Components in deep learning reference-based super resolution methods

引用

Procedia Computer Science 2024年 242卷 1243-1248页

作者： Jiayu Xue Junjie Liu Yong Shi School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 101408 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 Sino-Danish College University of Chinese Academy of Sciences Beijing 100049 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 USA

Reference-based super resolution (RefSR) aims to recover the lost details in a low-resolution image and generate a high-resolution result, guided by a high-resolution reference image with similar contents or textures. In contrast to the traditional single-image super-resolution, which focuses on the intrinsic properties of the single low-resolution image, the challenge of RefSR lies in matching and aggregating highly-related but misaligned reference images with low-resolution images. Several effective but complex designs have been proposed to address this challenge, which poses difficulties in implementing RefSR in real-world applications. In order to better understand the working mechanism of RefSR and design a more efficient and lightweight architecture, we provide a review about the essential components of the existing deep learning-based RefSR. We decompose and classify the common pipeline into four submodules according to the functionalities. Then, we summarize and describe the implementation details of the commonly-adopted approaches in each submodule. Finally, we discuss the challenges and promising research directions.

关键词： Reference-based super resolution Deep learning Feature matching Feature alignment

来源：评论

学校读者我要写书评

暂无评论

Adaptive Robust Multi-View Linex-Based Xgboost Model for Credit Risk Assessment

SSRN

引用

SSRN 2023年

作者： Tang, Jingjing Zhu, Guorui Li, Jiahui Tian, Yingjie School of Business Administration Faculty of Business Administration Southwestern University of Finance and Economics Chengdu611130 China Institute of Big Data Southwestern University of Finance and Economics Chengdu611130 China 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

Credit risk assessment is crucial for financial institutions. The data-driven methods regard the credit risk assessment as the class-imbalanced binary classification task since the non-default samples greatly outnumber default samples. Ensemble learning offers more advantages over traditional single classifier for credit risk assessment. Besides, the credit data can be extracted from multiple sources, such as personal credit data from financial institutions, personal tax payment data from government departments, telecommunications overdue data from public utilities, etc. They are typical multi-view data. How to fully exploit such multi-view and class-imbalanced data is the main challenge for the improvement of the credit risk assessment. This study proposes a cost-sensitive multi-view ensemble learning model called CSMEL. It firstly adapts the loss of XGBoost with the asymmetric LINEX loss function to construct the cost-sensitive base classifier, and then designs a multi-view ensemble learning framework for the combination of base classifiers. The asymmetry of Linex loss contributes to not only assign different weights to the misclassification errors from the non-default and default classes, but also make the base classifiers robust to noises. Extensive experiments on the Corel datasets and Credit risk datasets validate the effectiveness of the CSMEL model. © 2023, The Authors. All rights reserved.

关键词： Public utilities

来源：评论

学校读者我要写书评

暂无评论

Multi-view Feature Augmentation with Adaptive Class Activation Mapping

arXiv

引用

arXiv 2022年

作者： Gao, Xiang Tian, Yingjie Qi, Zhiquan School of Computer Science and Technology University of Chinese Academy of Sciences China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences China

We propose an end-to-end-trainable feature augmentation module built for image classification that extracts and exploits multi-view local features to boost model performance. Different from using global average pooling (GAP) to extract vectorized features from only the global view, we propose to sample and ensemble diverse multi-view local features to improve model robustness. To sample class-representative local features, we incorporate a simple auxiliary classifier head (comprising only one 1×1 convolutional layer) which efficiently and adaptively attends to class-discriminative local regions of feature maps via our proposed AdaCAM (Adaptive Class Activation Mapping). Extensive experiments demonstrate consistent and noticeable performance gains achieved by our multi-view feature augmentation module. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Explicit Unsupervised Feature Selection Based on Structured Graph and Locally Linear Embedding

SSRN

引用

SSRN 2023年

作者： Miao, Jianyu Zhao, Jingjing Yang, Tiejun Fan, Chao Tian, Yingjie Shi, Yong Xu, Mingliang School of Artificial Intelligence and Big Data Henan University of Technology Zhengzhou450001 China College of Information Science and Engineering Henan University of Technology Zhengzhou450001 China 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 School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou450001 China

Numerous redundant and irrelevant features, and outliers are usually contained in high-dimensional data whose presence, if ignored, can bring detrimental effects on the performance of data processing tasks. Feature selection as a trending topic in a great deal of domains has been greatly concerned, which can effectively deal with noise and outlier. In this work, we propose a novel unsupervised method that unifies the explicit feature selective matrix learning and structured graph learning into a framework. An explicit selection matrix only consisting of 0 and 1 are designed, which can be integrated into locally linear embedding, and can be effectively and efficiently solved with closed-form solution. Furthermore, we take into account the local consistency between the samples so that the low dimensional manifold structures of samples can be preserved to a better degree. Instead of using the pre-defined similarity matrix to construct graph, we make use of the way of learning to obtain the adaptive graph. Besides, for the purpose of exploiting the cluster structure of data, we impose a rank constraint on the graph. Notably, both explicit selection matrix and intrinsic structure are learned in low-dimensional feature subspace, and thus the proposed methodology is more straightforward. We present an effective and efficient algorithm for the resulting problem based on alternative optimization strategy, and establish its convergence and computational complexity analysis results. Extensive experiments verify that our proposed approach can significantly outperform advanced methods. © 2023, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Towards Unified Token Learning for Vision-Language Tracking

arXiv

引用

arXiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, Xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement

arXiv

引用

arXiv 2024年

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences 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

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

The Development of Green Olympic Games: A Comparison of CO2Emission Reduction Strategies between PyeongChang 2018 and Beijing 2022 9th

The Development of Green Olympic Games: A Comparison of CO2E...

引用

9th International Conference on Information Technology and Quantitative management, ITQM 2022

作者： Ding, Xuesong Jiang, Yilin Yang, Banban Su, Jingchun Chen, Liming Li, Na School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Chinese Academy of Fiscal Sciences Ministry of Finance Beijing100142 China Division of Sports Science and Physical Education Tsinghua University Beijing100084 China Division of Sports Science and Physical Education Tangshan Polytechnic College Tangshan063299 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 Sciences Beijing100190 China

The Olympic Games are striking a balance between economic and ecological benefits. Taking the 5 ice event venues of the 2018 PyeongChang Winter Olympic Games as the research object, the CO2 emissions under the 2018 PyeongChang Low-carbon scenario and 2022 Beijing Low-carbon scenario are compared. The empirical results show that, in terms of venue operation, the Beijing strategies can reduce CO2 emissions by 715.7 t compared with the PyeongChang strategies. In terms of the refrigerant escape, Beijing's adoption of CO2 refrigerant can reduce the emission of CO2 by 1202.2 t compared with the R404 refrigerant used in PyeongChang. This paper confirms the progress of the Green Winter Olympic Games, and may provide implications for the future host countries as well as the cities which in the green transformation. © 2022 The Author(s).

关键词： Refrigerants

来源：评论

学校读者我要写书评

暂无评论

Optimization Strategies for Client Drift in Federated Learning: A review 9th

Optimization Strategies for Client Drift in Federated Learni...

引用

9th International Conference on Information Technology and Quantitative management, ITQM 2022

作者： Shi, Yong Zhang, Yuanying Xiao, Yang Niu, Lingfeng 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 College of Information Sciences and Technology University of Nebraska at Omaha NE68182 United States School of Mathematical Sciences University of Chinese Academy of Sciences Beijing100190 China Faculty of Information Technology Beijing University of Technology Beijing100124 China

With the development of AI technology, there is an increasing awareness and concern about data privacy, and training data is becoming more and more fragmented. To make better use of this distributed data while ensuring privacy, federated learning is proposed, which can federate multiple distributed devices to train a machine learning model and does not exchange the raw training data. A key challenge in federated learning is that the distribution of data across clients is heterogeneous, which leads to client drift, that is, local model updates toward local optimal solutions, resulting in performance degradation of the global model. To address this problem, many federated learning algorithms have been proposed. In this paper, we provide a review of existing federated learning optimization strategies. In our opinion, the existing optimization strategies for client drift can be roughly classified into the following two categories: model aggregation and model training. We introduce these two categories separately. Finally, we present our perspectives on the future development. © 2022 The Author(s).

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

Research on the Rules of Scientists’ knowledge Sharing based on Interdisciplinary Measurement

引用

Procedia Computer Science 2022年 199卷 657-664页

作者： Yong Shi Yunong Wang 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 College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA

With the development of modern science, the adjustment of knowledge structure and the deepening of knowledge, the mode of single discipline research has been gradually broken, and interdisciplinary research has become a necessary way. All the information science and library science articles collected in the core collection of web of science from 1982 to 2020 are used for research and analysis. Through the research of interdisciplinary measurement index, this paper improves the existing interdisciplinary measurement index, uses Excel, Python and other tools to carry out data mining, cleaning, processing, analysis, and determines the interdisciplinary literature data defined in this paper. Finally, with vosviewer and other visual tools, this paper uses the citation network of bibliometrics, keywords co-occurrence and other ways to summarize interdisciplinary science’s law of knowledge sharing and provides suggestions and directions for future research.

关键词： Interdisciplinarity Disciplinary Similarity knowledge Sharing

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：