检索结果-内蒙古大学图书馆

Sample selection for noisy partial label learning with interactive contrastive learning

PATTERN RECOGNITION 2025年 166卷

作者： Yu, Xiaotong Sun, Shiding Tian, Yingjie Univ Chinese Acad Sci Sch Math Sci Beijing 100049 Peoples R China China Aerosp Sci & Ind Corp Def Technol R&T Ctr Beijing 100854 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 UCAS MOE Social Sci Lab Digital Econ Forecasts & Policy Beijing 100190 Peoples R China China Unicom Res Inst Beijing 100176 Peoples R China

In the context of weakly supervised learning, partial label learning (PLL) addresses situations where each training instance is associated with a set of partial labels, with only one being accurate. However, in complex realworld tasks, the restrictive assumption may be invalid which means the ground-truth may be outside the candidate label set. In this work, we loose the constraints and address the noisy label problem for PLL. First, we introduce a selection strategy, which enables deep models to select clean samples via the loss values of flipped and original images. Besides, we progressively identify the true labels of the selected samples and ensemble two models to acquire the knowledge of unselected samples. To extract better feature representations, we introduce pseudo-labeled interactive contrastive learning to aggregate cross-network information of all samples. Experimental results verify that our approach surpasses baseline methods on noisy PLL task with different levels of label noise.

关键词： Partial label learning Noisy label learning Contrastive learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

Meta-Wrapper: Differentiable Wrapping Operator for User Interest Selection in CTR Prediction

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2022年第11期44卷 8449-8464页

作者： Cao, Tianwei Xu, Qianqian Yang, Zhiyong Huang, Qingming Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 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 Key Lab Big Data Min & Knowledge Management BDKM Beijing 101408 Peoples R China Peng Cheng Lab Shenzhen 518055 Peoples R China

Click-through rate (CTR) prediction, whose goal is to predict the probability of the user to click on an item, has become increasingly significant in the recommender systems. Recently, some deep learning models with the ability to automatically extract the user interest from his/her behaviors have achieved great success. In these work, the attention mechanism is used to select the user interested items in historical behaviors, improving the performance of the CTR predictor. Normally, these attentive modules can be jointly trained with the base predictor by using gradient descents. In this paper, we regard user interest modeling as a feature selection problem, which we call user interest selection. For such a problem, we propose a novel approach under the framework of the wrapper method, which is named Meta-Wrapper. More specifically, we use a differentiable module as our wrapping operator and then recast its learning problem as a continuous bilevel optimization. Moreover, we use a meta-learning algorithm to solve the optimization and theoretically prove its convergence. Meanwhile, we also provide theoretical analysis to show that our proposed method 1) efficiencies the wrapper-based feature selection, and 2) achieves better resistance to overfitting. Finally, extensive experiments on three public datasets manifest the superiority of our method in boosting the performance of CTR prediction.

关键词： Feature extraction Predictive models Wrapping Frequency modulation Computational modeling Training Recommender systems Click-through rate prediction recommender system bilevel optimization meta-learning

来源：评论

学校读者我要写书评

暂无评论

Global Green Digital Economy: Challenges and Development: Preface for ITQM 2022

引用

Procedia Computer Science 2022年第C期214卷 1-3页

作者： Shi, Yong Li, Jianping Kou, Gang Berg, Daniel Tien, James College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States Research Centre on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China School of Business Administration Southwestern University of Finance and Economics Chengdu611130 China College of Engineering University of Miami Coral GablesFL33124 United States

来源：评论

学校读者我要写书评

暂无评论

Causal multi-label learning for image classification

引用

NEURAL NETWORKS 2023年 167卷 626-637页

作者： Tian, Yingjie Bai, Kunlong Yu, Xiaotong Zhu, Siyu Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 101408 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 UCAS MOE Social Sci Lab Digital Econ Forecasts & Policy Beijing 100190 Peoples R China

In this paper, we investigate the problem of causal image classification with multi-label learning. As multi-label learning involves a diversity of supervision signals, it is considered a challenging issue to solve. Previous approaches have attempted to improve performance by identifying label-related image areas or exploiting the co-occurrence of labels. However, these methods are often characterized by complicated procedures, tedious computations, and a lack of intuitive interpretations. To overcome these limitations, we propose a novel approach that incorporates the concept of causal inference, which has been shown to be beneficial in other computer vision problems. Our method, called causal multi-label learning (CMLL), enables the selection of multiple objects from the original image through a multi-class attention module. These objects are then subjected to causal intervention to learn the causal relationships between different labels. Our proposed approach is both elegant and effective, with low computational cost and few parameters required for the multi-class causal intervention approach. Extensive tests and ablation studies demonstrate that the proposed method significantly improves prediction performance without a significant increase in training and inference times.(c) 2023 Elsevier Ltd. All rights reserved.

关键词： Causal inference Multi -label image classification Deep learning Representation learning

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation

arXiv

引用

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

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：