检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

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 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Measuring China's Real Estate Financial Innovation from the Perspective of Government,Enterprises and the Public:Index Compilation and Its Spatial-Temporal Characteristics Analysis

引用

Journal of Systems Science and Information 2023年第1期11卷 1-34页

作者： Jichang DONG Lijun YIN Xiaoting LIU Xiuting LI School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100190China China Construction Second Engineering Bureau Co.Ltd Beijing 100070China

In recent years,China has witnessed the rapid development in housing finance,and there have emerged constantly real estate finance innovations;however,there exists no relevant index for measuring the innovations of China's real estate *** on the perspectives of the governments,enterprises and the public,this paper constructs the"innovation index of real estate finance"on a quarterly basis from 2009 to 2019,with the method of empowerment which combines the subjective method(analytic hierarchy process)and the objective one(range coefficient method).It clearly and concretely depicts the innovations in housing finance and the related temporal-spatial characteristics in China since the outbreak of the financial crisis in *** index covers 30 provinces,autonomous regions and municipalities directly under the central government,and analyzes its temporal and spatial *** findings show that there exist a strong spatial autocorrelation and a big regional difference in innovations.

关键词： governments enterprises public real estate finance innovation

来源：评论

学校读者我要写书评

暂无评论

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on Adaptive Perturbation on Federated Graph Learning 25

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on ...

引用

34th ACM Web Conference, WWW 2025

作者： Li, Ken Shi, Bin Wei, Jiazhe Dong, Bo School of Computer Science and Technology Xi’an Jiaotong University Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China School of Distance Education Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China

ISBN: (纸本)9798400712746

Federated Graph Learning (FedGL) is an emerging Federated Learning (FL) framework that learns the graph data from various clients to train better Graph Neural Networks(GNNs) model. Owing to concerns regarding the security of such framework, numerous studies have attempted to execute backdoor attacks on FedGL, with a particular focus on distributed backdoor attacks. However, all existing methods posting distributed backdoor attack on FedGL only focus on injecting distributed backdoor triggers into the training data of each malicious client, which will cause model performance degradation on original task and is not always effective when confronted with robust federated learning defense algorithms, leading to low success rate of attack. What’s more, the backdoor signals introduced by the malicious clients may be smoothed out by other clean signals from the honest clients, which potentially undermining the performance of the attack. To address the above significant shortcomings, we propose a non-intrusive graph distributed backdoor attack(NI-GDBA) that does not require backdoor triggers to be injected in the training data. Our attack trains an adaptive perturbation trigger generator model for each malicious client to learn the natural backdoor from the GNN model downloading from the server with the malicious client’s local data. In contrast to traditional distributed backdoor attacks on FedGL via trigger injection in training data, our attack on different datasets such as Molecules and Bioinformatics have higher attack success rate, stronger persistence and stealth, and has no negative impact on the performance of the global GNN model. We also explore the robustness of NI-GDBA under different defense strategies, and based on our extensive experimental studies, we show that our attack method is robust to current federated learning defense methods, thus it is necessary to consider non-intrusive distributed backdoor attacks on FedGL as a novel threat that requires custom d

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

EXISTENCE AND UNIQUENESS OF SOLUTIONS FOR UNCERTAIN NONLINEAR SWITCHED SYSTEMS WITH V-N JUMPS

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2025年第1期87卷 129-140页

作者： Jia, Zhifu Li, Cunlin School of Mathematics and Physics Suqian University Suqian223800 China [Ningxia Key Laboratory of intelligent information and Big Data Processing Governance and Social Management Research Center of Northwest Ethnic Regions North Minzu University Yinchuan China

In this paper, an uncertain nonlinear switched system with V-n jumps, characterized by its sensitivity to subjective uncertainties, is modeled using uncertain differential equations with V-n jumps. To account for the discontinuous jump behavior in each subsystem, a V-n jumps process associated with an uncertain Z-n jumps variable, defined by a jump uncertainty distribution, is introduced. Under the assumptions of linear growth and Lipschitz conditions, an existence and uniqueness theorem for the solutions of uncertain nonlinear switched systems with V-n jumps is established and rigorously proven. An illustrative example is provided to demonstrate the effectiveness and applicability of the theoretical results. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Uncertain systems

来源：评论

学校读者我要写书评

暂无评论

Representation learning via an integrated autoencoder for unsupervised domain adaptation

引用

Frontiers of Computer Science 2023年第5期17卷 75-87页

作者： Yi ZHU Xindong WU Jipeng QIANG Yunhao YUAN Yun LI School of Information Engineering Yangzhou UniversityYangzhou 225127China Key Laboratory of Knowledge Engineering with Big Data(Ministry of Education of China) Hefei University of TechnologyHefei 230009China School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230601China

The purpose of unsupervised domain adaptation is to use the knowledge of the source domain whose data distribution is different from that of the target domain for promoting the learning task in the target *** key bottleneck in unsupervised domain adaptation is how to obtain higher-level and more abstract feature representations between source and target domains which can bridge the chasm of domain ***,deep learning methods based on autoencoder have achieved sound performance in representation learning,and many dual or serial autoencoderbased methods take different characteristics of data into consideration for improving the effectiveness of unsupervised domain ***,most existing methods of autoencoders just serially connect the features generated by different autoencoders,which pose challenges for the discriminative representation learning and fail to find the real cross-domain *** address this problem,we propose a novel representation learning method based on an integrated autoencoders for unsupervised domain adaptation,called *** capture the inter-and inner-domain features of the raw data,two different autoencoders,which are the marginalized autoencoder with maximum mean discrepancy(mAE)and convolutional autoencoder(CAE)respectively,are proposed to learn different feature *** higher-level features are obtained by these two different autoencoders,a sparse autoencoder is introduced to compact these inter-and inner-domain *** addition,a whitening layer is embedded for features processed before the mAE to reduce redundant features inside a local *** results demonstrate the effectiveness of our proposed method compared with several state-of-the-art baseline methods.

关键词： unsupervised domain adaptation representation learning marginalized autoencoder convolutional autoen-coder sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

Class-view graph knowledge distillation: A new idea for learning MLPs on graphs

引用

NEUROCOMPUTING 2025年 637卷

作者： Tian, Yingjie Xu, Shaokai Li, Muyang Univ Chinese Acad Sci Sch Econ & Management Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Comp Sci & Technol Beijing 100049 Peoples R China Chinese Acad Sci Res Ctr Fictitious Econ & Data Sci Beijing 100190 Peoples R China Univ Chinese Acad Sci Key Lab Big Data Min & Knowledge Management Beijing 100190 Peoples R China

Graph Neural Networks (GNNs), while effective for processing non-Euclidean structured data, suffer from computationally intensive neighbor fetching, which hinders their deployment in low-latency applications. Cross-architecture graph knowledge distillation (KD), which trains high-performance Multi-layer Perceptrons (MLPs) to emulate teacher GNNs, offers a promising solution. However, existing GNN-MLP distillation methods rely on the sample-view KD paradigm, where student models directly mimic the teacher's parameter space. Given the fundamentally different architectures and parameter spaces of GNNs and MLPs, this direct mimicry approach limits effective knowledge transfer. Inspired by the inherent properties of MLPs, we propose a novel class-view KD paradigm for GNN-MLP distillation. Unlike sample-view KD, our method guides student MLPs to generate more discriminative parameter configurations within their own parameter space while preserving the similarity of prediction distributions with the teacher, rather than directly imitating the teacher's parameter configurations. Extensive experiments on public benchmark datasets demonstrate that class-view KD outperforms sample-view KD across various evaluation metrics and can be seamlessly integrated into existing GNN-MLP distillation methods to improve performance without additional computational cost. The code is available at https://***/xsk160/Class-View-Graph-KD.

关键词： Graph knowledge distillation Cross-architecture Class-view

来源：评论

学校读者我要写书评

暂无评论

Consistent estimation of the number of communities via regularized network embedding

引用

BIOMETRICS 2023年第3期79卷 2404-2416页

作者： Ren, Mingyang Zhang, Sanguo Wang, Junhui Chinese Univ Hong Kong Dept Stat Ma Liu Shui Hong Kong Peoples R China Univ Chinese Acad Sci Sch Math Sci Key Lab Big Data Min & Knowledge Management Beijing Peoples R China

The network analysis plays an important role in numerous application domains including biomedicine. Estimation of the number of communities is a fundamental and critical issue in network analysis. Most existing studies assume that the number of communities is known a priori, or lack of rigorous theoretical guarantee on the estimation consistency. In this paper, we propose a regularized network embedding model to simultaneously estimate the community structure and the number of communities in a unified formulation. The proposed model equips network embedding with a novel composite regularization term, which pushes the embedding vector toward its center and pushes similar community centers collapsed with each other. A rigorous theoretical analysis is conducted, establishing asymptotic consistency in terms of community detection and estimation of the number of communities. Extensive numerical experiments have also been conducted on both synthetic networks and brain functional connectivity network, which demonstrate the superior performance of the proposed method compared with existing alternatives.

关键词： brain network community detection fusion penalty latent space model stochastic block model

来源：评论

学校读者我要写书评

暂无评论

How China Deals with COVID-19 Pandemic

引用

INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING 2024年第1期23卷 17-35页

作者： Shi, Yong Qu, Yi Zhang, Linzi 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 Univ Nebraska Omaha Coll Informat Sci & Technol Omaha NE 68182 USA

Currently, the whole world is still suffering from the COVID-19 (variants) pandemic that has been lasting for over three years and resulted in countless losses. Since its outbreak at the end of 2019, China has first suffered, but quickly gained the upper hand through strict epidemic control and emergency management. Despite several recurrences of regional epidemics in 2022, both economic growth and people's livelihoods have been effectively safeguarded in China, with a regular prevention system established and social life recovery accomplished orderly. How does China deal with this pandemic? What practical measures taken and decisions made could be adopted and shared with other countries? In this paper, these issues are summarized and discussed as progressive lessons for the rest of the world. Though there's a major shift of pandemic policy in late 2022 and early 2023 in China, this study still provides insightful and beneficial implications to support decision- and policy-makings in future fights against any possible COVID-19 variants until the end of the pandemic.

关键词： COVID-19 pandemic China emergency management strategic decision making

来源：评论

学校读者我要写书评

暂无评论

A dynamic key node learning algorithm in evolving financial network: case study during the period of coronavirus 9th

A dynamic key node learning algorithm in evolving financial ...

引用

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

作者： Lu, Doudou Deng, Wei Xu, Yongyin Shi, Yong College of Big Data Statistics Guizhou University of Finance and Economics Guizhou550025 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

Finding an influential set of nodes in the interconnected network, whose activities would maximally influence the development of overall network, is a fundamental topic in finance, biology, social science, epidemic control and other scenarios with respect to network science. In recent years, some works are proposed to find key nodes via network connectivity measures, these studies assume a static environment, and besides, key nodes are calculated through pairwise connectivity, the number of connected components and other measures from the perspective of graph theory. However, these studies leave out of consideration on the dynamic evolving environment and causal relationships in the network. In this paper, we introduce a key node learning algorithm in an evolving financial network. The intuition of the algorithm is to model the causality of financial entities over the time, and the metrics for cascading networks are proposed to grade the entities in the network. In the experiment, the worldwide financial activities before and during the period of coronavirus are analyzed. The proposed metrics can effectively capture the influential entities and quantitatively describe these influences on the whole financial system. © 2022 The Authors. Published by Elsevier B.V.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Perfect Alignment May be Poisonous to Graph Contrastive Learning 41

Perfect Alignment May be Poisonous to Graph Contrastive Lear...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Jingyu Tang, Huayi Liu, Yong Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

Graph Contrastive Learning (GCL) aims to learn node representations by aligning positive pairs and separating negative ones. However, few of researchers have focused on the inner law behind specific augmentations used in graph-based learning. What kind of augmentation will help downstream performance, how does contrastive learning actually influence downstream tasks, and why the magnitude of augmentation matters so much? This paper seeks to address these questions by establishing a connection between augmentation and downstream performance. Our findings reveal that GCL contributes to downstream tasks mainly by separating different classes rather than gathering nodes of the same class. So perfect alignment and augmentation overlap which draw all intra-class samples the same can not fully explain the success of contrastive learning. Therefore, in order to understand how augmentation aids the contrastive learning process, we conduct further investigations into the generalization, finding that perfect alignment that draw positive pair the same could help contrastive loss but is poisonous to generalization, as a result, perfect alignment may not lead to best downstream performance, so specifically designed augmentation is needed to achieve appropriate alignment performance and improve downstream accuracy. We further analyse the result by information theory and graph spectrum theory and propose two simple but effective methods to verify the theories. The two methods could be easily applied to various GCL algorithms and extensive experiments are conducted to prove its effectiveness. The code is available at https://***/somebodyhh1/GRACEIS. Copyright 2024 by the author(s)

关键词： Contrastive 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：