检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Zhengyang Hu Song Kang Qunsong Zeng Kaibin Huang Yanchao Yang Department of Electrical and Electronic Engineering the University of Hong Kong School of Information Science and Technology University of Science and Technology of China and HKU Department of Electrical and Electronic Engineering and Musketeers Foundation Institute of Data Science the University of Hong Kong

Estimating mutual correlations between random variables or data streams is essential for intelligent behavior and decision-making. As a fundamental quantity for measuring statistical relationships, mutual information has been extensively studied and utilized for its generality and equitability. However, existing methods often lack the efficiency needed for real-time applications, such as test-time optimization of a neural network, or the differentiability required for end-to-end learning, like histograms. We introduce a neural network called InfoNet, which directly outputs mutual information estimations of data streams by leveraging the attention mechanism and the computational efficiency of deep learning infrastructures. By maximizing a dual formulation of mutual information through large-scale simulated training, our approach circumvents time-consuming test-time optimization and offers generalization ability. We evaluate the effectiveness and generalization of our proposed mutual information estimation scheme on various families of distributions and applications. Our results demonstrate that InfoNet and its training process provide a graceful efficiency-accuracy trade-off and order-preserving properties. Our code and models are available as a comprehensive toolbox to facilitate studies in different fields requiring real-time mutual information estimation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Control Through Wave PDE with State-Dependent Propagation Speed 42

Nonlinear Control Through Wave PDE with State-Dependent Prop...

引用

42nd Chinese Control Conference, CCC 2023

作者： Cai, Xiushan Lin, Yuhang Wang, Ping Ke, Changwu School of Data Science and Intelligent Engineering Xiamen Institute of Technology Xiamen361021 China College of Engineering North Carolina State University RaleighNC27695 United States College of Electrical Engineering and Automation Hubei Normal University Huangshi435002 China

ISBN: (纸本)9789887581543

We consider predictor control of a nonlinear ODE/wave PDE cascaded system with state-dependent propagation speed. First, the original cascaded system is transferred into a coupled hyperbolic PDE cascading with a nonlinear ODE by the first-step backstepping transformation. Further, this cascaded system is transferred into a pair of transport PDEs with state-dependent coefficients cascading into a nonlinear ODE by the second-step backstepping transformation. The key challenge is to prove the well-posedness and uniqueness of kernel equations, and design a compensator for the resulting cascaded system. Our design provides asymptotic stability and attraction region estimation for the closed-loop system since the propagation speed of wave depends on the ODE's state. An example is given to show the validity of the proposed design. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Decomposition of Difficulties in Complex Optimization Problems using a Bilevel Approach

Decomposition of Difficulties in Complex Optimization Proble...

引用

Congress on Evolutionary Computation

作者： Ankur Sinha Dhaval Pujara Hemant Kumar Singh Centre for Data Science and AI Indian Institute of Management Ahmedabad Gujarat India School of Engineering and Technology The University of New South Wales Canberra Australia

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Practical optimization problems may contain differ-ent kinds of difficulties that are often not tractable if one relies on a particular optimization method. Different optimization approaches offer different strengths that are good at tackling one or more difficulty in an optimization problem. For instance, evolutionary algorithms have a niche in handling complexities like discontinuity, non-differentiability, discreteness and non-convexity. However, evolutionary algorithms may get computationally expensive for mathematically well behaved problems with large number of variables for which classical mathematical programming approaches are better suited. In this paper, we demonstrate a decomposition strategy that allows us to synergistically apply two complementary approaches at the same time on a complex optimization problem. Evolutionary algorithms are useful in this context as their flexibility makes pairing with other solution approaches easy. The decomposition idea is a special case of bilevel optimization that separates the difficulties into two levels and assigns different approaches at each level that is better equipped at handling them. We demonstrate the benefits of the proposed decomposition idea on a wide range of test problems.

关键词： Heuristic algorithms Evolutionary computation Benchmark testing Complexity theory Classification algorithms Quadratic programming Optimization

来源：评论

学校读者我要写书评

暂无评论

Detecting the Human Activities of Aging People using Restricted Boltzmann Machines with Deep Learning Technique in IoT 3

Detecting the Human Activities of Aging People using Restric...

引用

3rd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2023

作者： Manimaran, M. Sasi Kumar, A. Natteshan, N.V.S. Baranitharan, K. Mahaveerakannan, R. Sudhakar, K. Sri Krishna Adithya College of Arts and Science Department of Computer Science Coimbatore India Srinivas University Institute of Engineering and Technology Department of Cloud Technology and Data Science Surathkal Dakshina Kannada District Mukka India S.A. Engineering College Department of Cse Chennai India Vsb Engineering College Department of Cse India Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha Institute of Medical and Technical Sciences Department of Ece Saveetha School of Engineering Tamil Nadu Chennai India

ISBN: (纸本)9781665462167

Approximately 962,000,000 persons worldwide are 60 or older. Despite the widespread adoption of techniques for human activity detection, there has been a dearth of study into the specific challenge of identifying the tasks performed by the elderly. Given the proliferation of wearable and mobile devices, the Internet of Healthcare Things is assuming a larger role in Human Activity Recognition (HAR). This article focuses on assisting the elderly by tracking their movements in both indoor and outdoor settings. The dataset includes human actions like sitting, walking, ascending and descending stairs, standing, and lying down. Here, how deep learning might improve HAR in Internet of Home Things settings has been examined. For better HAR results, a semi-supervised deep learning framework has been developed that makes effective use of the imperfectly labelled sensor data in order to fine-tune the classifier learning model. An intelligent auto-labelling system is built on top of Deep Q-Network to enhance learning performance in Internet of Things (IoT) environment and address the issue of insufficient labelled samples. Finally, real-world data is used in trial and evaluation to prove the method's utility and efficacy. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

FedAA: A Reinforcement Learning Perspective on Adaptive Aggregation for Fair and Robust Federated Learning

arXiv

引用

arXiv 2024年

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Our code is available at https://***/Gp1g/FedAA. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

M-Graphormer: Multi-Channel Graph Transformer for Node Representation Learning

引用

IEEE Transactions on Big data 2024年

作者： Chang, Xinglong Wang, Jianrong Wen, Mingxiang Wang, Yingkui Huang, Yuxiao Tianjin University School of New Media and Communication Tianjin300350 China Tianjin Renai College School of Intelligent Computing Engineering Tianjin301636 China George Washington University NW Department of Data Science WashingtonDC20052 United States

In recent years, the Graph Transformer has demonstrated superiority on various graph-level tasks by facilitating global interactions among nodes. However, as for node-level tasks, the existing Graph Transformer cannot perform as well as expected. Actually, a node in a real-world graph does not necessarily have relationships with every other node, and this global interaction weakens node features. This raises a fundamental question: should we partition out an appropriate interaction channel based on graph structure so that noisy and irrelevant information will be filtered and every node can aggregate information in the optimal channel? We first perform a series of experiments on manually created graphs with varying homophily ratios. Surprisingly, we observe that different graph structures indeed require distinct optimal interaction channels. This leads us to ask whether we can develop a partitioning rule that ensures each node interacts with relevant and valuable targets. To overcome this challenge, we propose a novel Graph Transformer named Multi-channel Graphormer. The model is evaluated on six network datasets with different homophily ratios for the node classification task. Moreover, comprehensive experiments are conducted on two real datasets for the recommendation task. Experimental results show that the Multi-channel Graphormer surpasses state-of-the-art baselines, demonstrating superior performance. © 2015 IEEE.

关键词： Graph transformer homophily node classification

来源：评论

学校读者我要写书评

暂无评论

Robust Correlation Clustering Problem with Locally Bounded Disagreements

Robust Correlation Clustering Problem with Locally Bounded D...

引用

作者： Ji, Sai Li, Min Liang, Mei Zhang, Zhenning Institute of Mathematics Hebei University of Technology Tianjin300401 China School of Mathematics and Statistics Shandong Normal University Jinan250358 China College of Statistics and Data Science Beijing University of Technology Beijing100124 China Beijing University of Technology Department of Operations Research and Information Engineering Beijing100124 China

Min-max disagreements are an important generalization of the correlation clustering problem (CorCP). It can be defined as follows. Given a marked complete graph G=(V, E), each edge in the graph is marked by a positive label '+' or a negative label '-' based on the similarity of the connected vertices. The goal is to find a clustering C of vertices V, so as to minimize the number of disagreements at the vertex with the most disagreements. Here, the disagreements are the positive cut edges and the negative non-cut edges produced by clustering C. This paper considers two robust min-max disagreements: min-max disagreements with outliers and min-max disagreements with penalties. Given parameter δ\in(0,1/14), we first provide a threshold-based iterative clustering algorithm based on LP-rounding technique, which is a (1/δ, 7/(1-14δ))-bi-criteria approximation algorithm for both the min-max disagreements with outliers and the min-max disagreements with outliers on one-sided complete bipartite graphs. Next, we verify that the above algorithm can achieve an approximation ratio of 21 for min-max disagreements with penalties when we set parameter δ=1/21. © 1996-2012 Tsinghua University Press.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

Attack-in-the-Chain: Bootstrapping Large Language Models for Attacks Against Black-Box Neural Ranking Models 39

Attack-in-the-Chain: Bootstrapping Large Language Models for...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liu, Yu-An Zhang, Ruqing Guo, Jiafeng de Rijke, Maarten Fan, Yixing Cheng, Xueqi CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China University of Amsterdam Amsterdam Netherlands

ISBN: (纸本)157735897X

Neural ranking models (NRMs) have been shown to be highly effective in terms of retrieval performance. Unfortunately, they have also displayed a higher degree of sensitivity to attacks than previous generation models. To help expose and address this lack of robustness, we introduce a novel ranking attack framework named Attack-in-the-Chain, which tracks interactions between large language models (LLMs) and NRMs based on chain-of-thought (CoT) prompting to generate adversarial examples under black-box settings. Our approach starts by identifying anchor documents with higher ranking positions than the target document as nodes in the reasoning chain. We then dynamically assign the number of perturbation words to each node and prompt LLMs to execute attacks. Finally, we verify the attack performance of all nodes at each reasoning step and proceed to generate the next reasoning step. Empirical results on two web search benchmarks show the effectiveness of our method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MVAM: Multi-View Attention Method for Fine-Grained Image-Text Matching 47th

MVAM: Multi-View Attention Method for Fine-Grained Image-Te...

引用

47th European Conference on Information Retrieval, ECIR 2025

作者： Cui, Wanqing Cheng, Rui Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Alibaba Group Beijing China

ISBN: (纸本)9783031887109

Existing two-stream models, such as CLIP, encode images and text through independent representations, showing good performance while ensuring retrieval speed, have attracted attention from industry and academia. However, the single representation often struggles to capture complex content fully. Such models may ignore fine-grained information during matching, resulting in suboptimal retrieval results. To overcome this limitation and enhance the performance of two-stream models, we propose a Multi-View Atention Method (MVAM) for image-text matching. This approach leverages diverse attention heads with unique view codes to learn multiple representations for images and text, which are then concatenated for matching. We also incorporate a diversity objective to explicitly encourage attention heads to focus on distinct aspects of the input data, capturing complementary fine-grained details. This diversity enables the model to represent image-text pairs from multiple perspectives, ensuring a more comprehensive understanding and alignment of critical content. Our method allows models to encode images and text from different perspectives and focus on more critical details, leading to better matching performance. Our experiments on MSCOCO and Flickr30K demonstrate enhancements over existing models, and further case studies reveal that different attention heads can focus on distinct content, achieving more comprehensive representations. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Disaster Management Redefined: Integrating SVM-AE Techniques with Remote Sensing and Meteorological data

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 294-308页

作者： Priyadharshini, L. Dhanke, Jyoti A. Patil, R.N. Swapna, B. Kalyani, Kapula Syamala, Maganti Deivasigamani, Shanmugavel Saveetha School of Law Saveetha Institute of Medical and Technical Science Chennai India Department of Engineering Science (Mathematics) Bharati Vidyapeeth’s College of Engineering Lavale Pune India Department of Mechanical Engineering Bharati Vidyapeeth’s College of Engineering Lavale Pune India Department of ECE Dr. M.G.R. Educational and Research Institute Chennai India Department of Electronics and Communication Engineering Aditya College of Engineering and Technology Andhra Pradesh Surampalem 533437 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation AP Vaddeswaram Guntur India Department of Artificial Intelligence and Data Science Jeppiaar Institute of Technology Anna University Tamilnadu Chennai India

This study presents a novel hybrid model, the Support Vector Autoencoder (SVAE), designed to enhance disaster management through the integration of Support Vector Machines (SVM) and Autoencoders (AE). By leveraging the strengths of both machine learning techniques, the SVAE model offers improved accuracy and reliability in predicting and managing natural disasters. The methodology involves comprehensive data collection from Sentinel-2 satellite imagery and Global Precipitation Measurement (GPM) mission data, supplemented by historical disaster records from the Emergency Events database (EM-DAT). After rigorous preprocessing, key features such as the Normalized Difference Vegetation Index (NDVI), land surface temperature (LST), soil moisture content, and various meteorological parameters are extracted. These features are then normalized and used to train the SVM for supervised learning and the AE for unsupervised learning. The outputs of these modules are integrated through a fusion layer, which combines classification scores and anomaly detection signals to generate a final risk score. Performance comparison with other models, including Random Forest, k-NN, Decision Tree, and Naive Bayes, demonstrates that the SVAE model achieves superior accuracy, precision, recall, and F1-score. The proposed model’s accuracy reaches 97%, significantly outperforming other techniques in anomaly detection and risk assessment. The results indicate that the SVAE model is a robust tool for enhancing disaster preparedness and mitigation efforts, providing timely and actionable insights to decision-makers. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Autoencoder (AE) Disaster management Emergency Events database (EM-DAT) Global Precipitation Measurement (GPM) Machine learning Normalized Difference Vegetation Index (NDVI) Sentinel-2 Satellite Imagery Support Vector Autoencoder (SVAE) Support Vector Machine (SVM)

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：