检索结果-内蒙古大学图书馆

Analyzing the Convergence of Federated Learning with Biased Client Participation 9th

学校读者我要写书评

暂无评论

Analyzing the Convergence of Federated Learning with Bias...

19th International Conference on Advanced data Mining and Applications, ADMA 2023

作者： Tan, Lei Hu, Miao Zhou, Yipeng Wu, Di School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou510006 China School of Computing Faculty of Science and Engineering Macquarie University SydneyNSW2109 Australia

ISBN: (纸本)9783031466632

Federated Learning (FL) is a promising decentralized machine learning framework that enables a massive number of clients (e.g., smartphones) to collaboratively train a global model over the Internet without sacrificing their privacy. Though FL’s efficacy in non-convex problems is proven, its convergence amidst biased client participation lacks theoretical study. In this paper, we analyze the convergence of FedAvg on non-convex problems, which is the most renowned FL algorithm. We assume even data distribution but non-IID among clients, and elucidate the convergence rate of FedAvg in situations characterized by biased client participation. Our analysis reveals that biased client participation can significantly reduce the precision of the FL model. We validate this through trace-driven experiments, demonstrating that unbiased client participation results in 11% to 50% higher test accuracy compared to extremely biased client participation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Artificial intelligence

Brain-inspired artificial intelligence research: A review

学校读者我要写书评

暂无评论

science China(Technological sciences) 2024年第8期67卷 2282-2296页

作者： WANG GuoYin BAO HuaNan LIU Qun ZHOU TianGang WU Si HUANG TieJun YU ZhaoFei LU CeWu GONG YiHong ZHANG ZhaoXiang HE Sheng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and TelecommunicationsChongqing 400065China Key Laboratory of Cyberspace Big Data Intelligent Security Chongqing University of Posts and TelecommunicationsChongqing 400065China College of Computer and Information Science Chongqing Normal UniversityChongqing 401331China State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China School of Psychological and Cognitive Sciences Peking UniversityBeijing 100871China State Key Laboratory of Multimedia Information Processing School of Computer SciencePeking UniversityBeijing 100871China Department of Computer Science School of ElectronicsInformation and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electronic and Information Engineering Xi’an Jiaotong UniversityXi’an 710049China The Center for Research on Intelligent Perception and Computing Institute of AutomationChinese Academy of SciencesBeijing 100190China Institute of Biophysics Chinese Academy of SciencesBeijing 100101China

Artificial intelligence(AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general AI, this study contains a review of the role of cognitive science in inspiring the development of the three mainstream academic branches of AI based on the three-layer framework proposed by David Marr, and the limitations of the current development of AI are explored and analyzed. The differences and inconsistencies between the cognition mechanisms of the human brain and the computation mechanisms of AI systems are analyzed. They are found to be the cause of the differences and contradictions between the cognition and behavior of AI systems and humans. Additionally, eight important research directions and their scientific issues that need to focus on braininspired AI research are proposed: highly imitated bionic information processing, a large-scale deep learning model that balances structure and function, multi-granularity joint problem solving bidirectionally driven by data and knowledge, AI models that simulate specific brain structures, a collaborative processing mechanism with the physical separation of perceptual processing and interpretive analysis, embodied intelligence that integrates the brain cognitive mechanism and AI computation mechanisms,intelligence simulation from individual intelligence to group intelligence(social intelligence), and AI-assisted brain cognitive intelligence.

关键词： artificial intelligence cognitive science brain science intelligence science large language model

ADEdgeDrop: Adversarial Edge Dropping for Robust Graph Neural Networks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Zhaoliang Wu, Zhihao Sadikaj, Ylli Plant, Claudia Dai, Hong-Ning Wang, Shiping Cheung, Yiu-Ming Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou350116 China Department of Computer Science Hong Kong Baptist University Hong Kong Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Faculty of Computer Science and with the research network Data Science @ Uni Vienna University of Vienna Vienna1090 Austria

Although Graph Neural Networks (GNNs) have exhibited the powerful ability to gather graph-structured information from neighborhood nodes via various message-passing mechanisms, the performance of GNNs is limited by poor generalization and fragile robustness caused by noisy and redundant graph data. As a prominent solution, Graph Augmentation Learning (GAL) has recently received increasing attention in the literature. Among the existing GAL approaches, edge-dropping methods that randomly remove edges from a graph during training are effective techniques to improve the robustness of GNNs. However, randomly dropping edges often results in bypassing critical edges. Consequently, the effectiveness of message passing is weakened. In this paper, we propose a novel adversarial edgedropping method (ADEdgeDrop) that leverages an adversarial edge predictor guiding the removal of edges, which can be flexibly incorporated into diverse GNN backbones. Employing an adversarial training framework, the edge predictor utilizes the line graph transformed from the original graph to estimate the edges to be dropped, which improves the interpretability of the edge-dropping method. The proposed ADEdgeDrop is optimized alternately by stochastic gradient descent and projected gradient descent. Comprehensive experiments on eight graph benchmark datasets demonstrate that the proposed ADEdgeDrop outperforms state-of-the-art baselines across various GNN backbones, demonstrating improved generalization and robustness. Copyright © 2024, The Authors. All rights reserved.

关键词： Adversarial machine learning

Efficient Convolutional Forward Modeling and Sparse Coding in Multichannel Imaging

学校读者我要写书评

暂无评论

Efficient Convolutional Forward Modeling and Sparse Coding i...

European Signal processing Conference (EUSIPCO)

作者： Han Wang Yhonatan Kvich Eduardo Pérez Florian Römer Yonina C. Eldar Applied AI Signal Processing and Data Analysis Fraunhofer Institute for Nondestructive Testing Saarbrücken Germany Dept. Electronic Measurements and Signal Processing Technische Universität Ilmenau Ilmenau Germany Faculty of Math and Computer Science Weizmann Institute of Science Rehovot Israel

ISBN: (数字)9789464593617

ISBN: (纸本)9798331519773

This study considers the Block-Toeplitz structural properties inherent in traditional multichannel forward model matrices, using Full Matrix Capture (FMC) in ultrasonic testing as a case study. We propose an analytical convolutional forward model that transforms reflectivity maps into FMC data. Our findings demonstrate that the convolutional model excels over its matrix-based counterpart in terms of computational efficiency and storage requirements. This accelerated forward modeling approach holds significant potential for various inverse problems, notably enhancing Sparse Signal Recovery (SSR) within the context LASSO regression, which facilitates efficient Convolutional Sparse Coding (CSC) algorithms. Additionally, we explore the integration of Convolutional Neural Networks (CNNs) for the forward model, employing deep unfolding to implement the Learned Block Convolutional ISTA (BC-LISTA).

关键词： Convolutional codes Adaptation models Convolution Computational modeling Signal processing algorithms Imaging Transforms Encoding Computational efficiency Sparse matrices

Efficient Convolutional Forward Modeling and Sparse Coding in Multichannel Imaging

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Wang, Han Kvich, Yhonatan Pérez, Eduardo Römer, Florian Eldar, Yonina C. Applied AI Signal Processing and Data Analysis Fraunhofer Institute for Nondestructive Testing Saarbrücken Germany Faculty of Math and Computer Science Weizmann Institute of Science Rehovot Israel Dept. Electronic Measurements and Signal Processing Technische Universität Ilmenau Ilmenau Germany

关键词： Ultrasonic testing

Supervised Anomaly Detection for Production Line Images using data Augmentation and Convolutional Neural Network

学校读者我要写书评

暂无评论

Supervised Anomaly Detection for Production Line Images usin...

International Conference on Emerging Technologies and Factory Automation (ETFA)

作者： Saara Asif Muhammad Uzair Akmal Leonid Koval Simon Knollmeyer Selvine G. Mathias Daniel Grossmann AI Motion Technische Hochschule Ingolstadt Ingolstadt Germany AI Motion Bavaria Technische Hochschule Ingolstadt Ingolstadt Germany Faculty of Computer Science and Data Processing Technische Hochschule Ingolstadt Ingolstadt Germany

ISBN: (数字)9798350361230

ISBN: (纸本)9798350361247

In the manufacturing industry, automated optical inspection aims to improve the detection and classification of anomalies by utilizing artificial intelligence and computer vision techniques to enhance quality control processes and minimize production defects. However, this automated system faces significant challenges, particularly regarding the detection of anomalies due to predominance of normal instances over defected ones. Addressing this imbalance is crucial for effective real-time anomaly detection particularly in images captured by Airbag Sensors among other automotive parts. Earlier contributions in domain-specific fields commonly relied on traditional computer vision methods, while recent systems are increasingly using deep learning techniques. Utilizing various data augmentation techniques ensures a more balanced representation of anomalies in the dataset, thereby enhancing the accuracy of the detection process. Moreover, it also enhances the robustness and generalization of the anomaly detection model by exposing it to a more diverse range of instances during training. Such work has not been carried out to augment Airbag Sensor images for analysis through a deep learner. Accordingly, this paper introduces a framework that employs data augmentation techniques for Convolutional Neural Networks (CNNs). The proposed system, based on data augmentation and CNN, significantly improves the performance for anomaly detection in Airbag Sensor images with a classification accuracy on the unaugmented dataset being 53 % which improves to 90% with augmentation.

关键词： Image sensors Training computer vision Accuracy Production data augmentation Sensor systems Robustness Convolutional neural networks Anomaly detection

Advancements in Content-Based Image Retrieval: A Comprehensive Survey of Relevance Feedback Techniques

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Qazanfari, Hamed Alyan Nezhadi, Mohammad M. Khoshdaregi, Zohreh Nozari Image Processing and Data Mining Lab Shahrood University of Technology Shahrood Iran Faculty of Science University of Science and Technology of Mazandaran Behshahr Iran Department of Computer Engineering University of Bojnord Iran

Content-based image retrieval (CBIR) systems have emerged as crucial tools in the field of computer vision, allowing for image search based on visual content rather than relying solely on metadata. This survey paper presents a comprehensive overview of CBIR, emphasizing its role in object detection and its potential to identify and retrieve visually similar images based on content features. Challenges faced by CBIR systems, including the semantic gap and scalability, are discussed, along with potential solutions. It elaborates on the semantic gap, which arises from the disparity between low-level features and high-level semantic concepts, and explores approaches to bridge this gap. One notable solution is the integration of relevance feedback (RF), empowering users to provide feedback on retrieved images and refine search results iteratively. The survey encompasses long-term and short-term learning approaches that leverage RF for enhanced CBIR accuracy and relevance. These methods focus on weight optimization and the utilization of active learning algorithms to select samples for training classifiers. Furthermore, the paper investigates machine learning techniques and the utilization of deep learning and convolutional neural networks to enhance CBIR performance. This survey paper plays a significant role in advancing the understanding of CBIR and RF techniques. It guides researchers and practitioners in comprehending existing methodologies, challenges, and potential solutions while fostering knowledge dissemination and identifying research gaps. By addressing future research directions, it sets the stage for advancements in CBIR that will enhance retrieval accuracy, usability, and effectiveness in various application domains. © 2023, CC BY.

关键词： Object detection

A Fast and Effective Multiple Kernel Clustering Method on Incomplete data

学校读者我要写书评

暂无评论

computers, Materials & Continua 2021年第4期67卷 267-284页

作者： Lingyun Xiang Guohan Zhao Qian Li Gwang-Jun Kim Osama Alfarraj Amr Tolba Changsha Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation School of Computer and Communication EngineeringChangsha University of Science and TechnologyChangsha410114China Hunan Key Laboratory of Smart Roadway and Cooperative Vehicle-Infrastructure Systems Changsha University of Science and TechnologyChangsha410114China Faculty of Engineering and Information Technology Global Big Data Technologies CentreUniversity of Technology SydneyUltimoNSW2007Australia Department of Computer Engineering Chonnam National UniversityGwangju61186Korea Computer Science Department Community CollegeKing Saud UniversityRiyadh11437Saudi Arabia Department of Mathematics and Computer Science Faculty of ScienceMenoua UniversityShebin-El-kom32511Egyp

Multiple kernel clustering is an unsupervised data analysis method that has been used in various scenarios where data is easy to be collected but hard to be ***,multiple kernel clustering for incomplete data is a critical yet challenging *** the existing absent multiple kernel clustering methods have achieved remarkable performance on this task,they may fail when data has a high value-missing rate,and they may easily fall into a local *** address these problems,in this paper,we propose an absent multiple kernel clustering(AMKC)method on incomplete *** AMKC method rst clusters the initialized incomplete ***,it constructs a new multiple-kernel-based data space,referred to as K-space,from multiple sources to learn kernel combination ***,it seamlessly integrates an incomplete-kernel-imputation objective,a multiple-kernel-learning objective,and a kernel-clustering objective in order to achieve absent multiple kernel *** three stages in this process are carried out simultaneously until the convergence condition is *** on six datasets with various characteristics demonstrate that the kernel imputation and clustering performance of the proposed method is signicantly better than state-of-the-art ***,the proposed method gains fast convergence speed.

关键词： Multiple kernel clustering absent-kernel imputation incomplete data kernel k-means clustering

AGNN: Alternating Graph-Regularized Neural Networks to Alleviate Over-Smoothing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Zhaoliang Wu, Zhihao Lin, Zhenghong Wang, Shiping Plant, Claudia Guo, Wenzhong The College of Computer and Data Science Fuzhou University Fuzhou350116 China The Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China The Faculty of Computer Science Austria The research network Data Science @ Uni Vienna University of Vienna Vienna1090 Austria

Graph Convolutional Network (GCN) with the powerful capacity to explore graph-structural data has gained noticeable success in recent years. Nonetheless, most of the existing GCN-based models suffer from the notorious over-smoothing issue, owing to which shallow networks are extensively adopted. This may be problematic for complex graph datasets because a deeper GCN should be beneficial to propagating information across remote neighbors. Recent works have devoted effort to addressing over-smoothing problems, including establishing residual connection structure or fusing predictions from multi-layer models. Because of the indistinguishable embeddings from deep layers, it is reasonable to generate more reliable predictions before conducting the combination of outputs from various layers. In light of this, we propose an Alternating Graph-regularized Neural Network (AGNN) composed of Graph Convolutional Layer (GCL) and Graph Embedding Layer (GEL). GEL is derived from the graph-regularized optimization containing Laplacian embedding term, which can alleviate the over-smoothing problem by periodic projection from the low-order feature space onto the high-order space. With more distinguishable features of distinct layers, an improved Adaboost strategy is utilized to aggregate outputs from each layer, which explores integrated embeddings of multi-hop neighbors. The proposed model is evaluated via a large number of experiments including performance comparison with some multi-layer or multi-order graph neural networks, which reveals the superior performance improvement of AGNN compared with state-of-the-art models. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings