检索结果-内蒙古大学图书馆

The Journal of Machine Learning Research 2024年第1期25卷 17738-17789页

作者： Gabriel Rioux Ziv Goldfeld Kengo Kato Center for Applied Mathematics Cornell University Ithaca NY School of Electrical and Computer Engineering Cornell University Ithaca NY Department of Statistics and Data Science Cornell University Ithaca NY

The Gromov-Wasserstein (GW) distance quantifies discrepancy between metric measure spaces and provides a natural framework for aligning heterogeneous datasets. Alas, as exact computation of GW alignment is NP-complete, entropic regularization provides an avenue towards a computationally tractable proxy. Leveraging a recently derived variational representation for the quadratic entropic GW (EGW) distance, this work derives the first efficient algorithms for solving the EGW problem subject to formal, nonasymptotic convergence guarantees. To that end, we derive smoothness and convexity properties of the objective in this variational problem, which enables its resolution by the accelerated gradient method. Our algorithms employ Sinkhorn's fixed point iterations to compute an approximate gradient, which we model as an inexact oracle. We furnish convergence rates towards local and even global solutions (the latter holds under a precise quantitative condition on the regularization parameter), characterize the effects of gradient inexactness, and prove that stationary points of the EGW problem converge towards a stationary point of the unregularized GW problem, in the limit of vanishing regularization. We provide numerical experiments that validate our theory and empirically demonstrate the state-of-the-art empirical performance of our algorithm.

关键词： Algorithms convergence rate global guarantees Gromov-Wasserstein distances entropic regularization inexact gradient methods

来源：评论

学校读者我要写书评

暂无评论

Innovative Healthcare Advancements: Harnessing Artificial and Human Intelligence for Bionic Solutions

Innovative Healthcare Advancements: Harnessing Artificial an...

引用

2024 OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4.0, OTCON 2024

作者： Sapkal, Samruddhi Jadhav, Sulaxan Mallikarjun, P. Shamim, Rejuwan Ul Islam, Atowar Bamane, Kalyan D y Patil International University Artificial Intelligence and Machine Learning Pune Akurdi411044 India D y Patil International University Pune Akurdi411044 India Malla Reddy Engineering College Jntuh Department of Electrical and Electronic Engineering Hyderabad India Maharishi University of Information Technology School of Data Science Noida India University of Science and Technology Meghalaya Department of Computer Science and Electronics Ri-Bhoi Techno city Kiling Road Meghalaya Baridua793101 India D y Patil College of Engineering Department of Information Technology Pune Akurdi India

ISBN: (纸本)9798350373783

According to initial data, individuals who have been diagnosed with type 2 diabetes (T2DM) appear to be at a more chances of evolving breast cancer compared to those who have not received a T2DM diagnosis. The primary goal of the research was to estimate the efficacy of three dissimilar methods in forecasting the probability of breast cancer in T2DM patients with diverse attributes. To achieve this objective, a danger expectation model was created for breast cancer in individuals with T2DM using the primary *** ensure a comprehensive analysis, we also gathered information on potential factors that may predict the growth of breast cancer. As the population sample size was restricted, we utilized Synthetic Minority Oversampling Technology to amplify the quantity of accessible data. Random assignment of data points to training or test sets was conducted at a ratio of roughly 39 to 1. Three distinct models, specifically Artificial Neural Network (ANN), Logistic Regression (LR), and Random Forest (RF), were assessed for effectiveness using a range of performance criteria, including as F1 score, area under the receiver operation characteristic curves, recalled, and correctness. (AUC). AUC values for these models were as follows: LR had an AUC of 0.834, ANN had an AUC of 0.865, and RF had an AUC of 0.959, with RF having the greatest AUC. According to our study, the Random Forest model outperformed the LR and ANN models in correctly estimating the incidence of breast cancer in people with T2DM. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Multiclass skin lesion classification using deep learning networks optimal information fusion

引用

Discover Applied sciences 2024年第6期6卷 1-13页

作者： Khan, Muhammad Attique Hamza, Ameer Shabaz, Mohammad Kadry, Seifeine Rubab, Saddaf Bilal, Muhammad Abdullah Akbar, Muhammad Naeem Kesavan, Suresh Manic Department of Computer Science HITEC University Taxila Pakistan Model Institute of Engineering and Technology Jammu India Department of Applied Data Science Noroff University College Oslo Norway Department of Computer Engineering College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of CS SEECS NUST Islamabad Pakistan National University of Sciences and Technology (NUST) Islamabad Pakistan Department of Electrical and Communication Engineering National University of Science and Technology Muscat Sultanate of Oman

A serious, all-encompassing, and deadly cancer that affects every part of the body is skin cancer. The most prevalent causes of skin lesions are UV radiation, which can damage human skin, and moles. If skin cancer is discovered early, it may be adequately treated. In order to diagnose skin lesions with less effort, dermatologists are increasingly turning to machine learning (ML) techniques and computer-aided diagnostic (CAD) systems. This paper proposes a computerized method for multiclass lesion classification using a fusion of optimal deep-learning model features. The dataset used in this work, ISIC2018, is imbalanced; therefore, augmentation is performed based on a few mathematical operations. After that, two pre-trained deep learning models (DarkNet-19 and MobileNet-V2) have been fine-tuned and trained on the selected dataset. After training, features are extracted from the average pool layer and optimized using a hybrid firefly optimization technique. The selected features are fused in two ways: (i) original serial approach and (ii) proposed threshold approach. Machine learning classifiers are used to classify the chosen features at the end. Using the ISIC2018 dataset, the experimental procedure produced an accuracy of 89.0%. Whereas, 87.34, 87.57, and 87.45 are sensitivity, precision, and F1 score respectively. At the end, comparison is also conducted with recent techniques, and it shows the proposed method shows improved accuracy along with other performance measures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Redundancy-Free Self-Supervised Relational Learning for Graph Clustering

arXiv

引用

arXiv 2023年

作者： Yi, Si-Yu Ju, Wei Qin, Yifang Luo, Xiao Liu, Luchen Zhou, Yong-Dao Zhang, Ming School of Statistics and Data Science Nankai University Tianjin300071 China School of Computer Science Peking University Beijing100871 China Department of Computer Science University of California Los Angeles90095 United States

Graph clustering, which learns the node representations for effective cluster assignments, is a fundamental yet challenging task in data analysis and has received considerable attention accompanied by graph neural networks in recent years. However, most existing methods overlook the inherent relational information among the non-independent and non-identically distributed nodes in a graph. Due to the lack of exploration of relational attributes, the semantic information of the graph-structured data fails to be fully exploited which leads to poor clustering performance. In this paper, we propose a novel self-supervised deep graph clustering method named Relational Redundancy-Free Graph Clustering (R2FGC) to tackle the problem. It extracts the attribute- and structure-level relational information from both global and local views based on an autoencoder and a graph autoencoder. To obtain effective representations of the semantic information, we preserve the consistent relation among augmented nodes, whereas the redundant relation is further reduced for learning discriminative embeddings. In addition, a simple yet valid strategy is utilized to alleviate the over-smoothing issue. Extensive experiments are performed on widely used benchmark datasets to validate the superiority of our R2FGC over state-of-the-art baselines. Our codes are available at https://***/yisiyu95/R2FGC. © 2023, CC BY.

关键词： Redundancy

来源：评论

学校读者我要写书评

暂无评论

Expediting Distributed GNN Training with Feature-only Partition and Optimized Communication Planning

Expediting Distributed GNN Training with Feature-only Partit...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Bingqian Du Jun Liu Ziyue Luo Chuan Wu Qiankun Zhang Hai Jin 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 Wuhan China Department of Electrical and Computer Engineering The Ohio State University USA Department of Computer Science The University of Hong Kong Hong Kong School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350383508

ISBN: (纸本)9798350383515

Feature-only partition of large graph data in distributed Graph Neural Network (GNN) training offers advantages over commonly adopted graph structure partition, such as minimal graph preprocessing cost and elimination of cross-worker subgraph sampling burdens. Nonetheless, performance bottleneck of GNN training with feature-only partitions still largely lies in the substantial communication overhead due to cross-worker feature fetching. To reduce the communication overhead and expedite distributed training, we first investigate and answer two key questions on convergence behaviors of GNN model in feature-partition based distribute GNN training: 1) As no worker holds a complete copy of each feature, can gradient exchange among workers compensate for the information loss due to incomplete local features? 2) If the answer to the first question is negative, is feature fetching in every training iteration of the GNN model necessary to ensure model convergence? Based on our theoretical findings on these questions, we derive an optimal communication plan that decides the frequency for feature fetching during the training process, taking into account bandwidth levels among workers and striking a balance between model loss and training time. Extensive evaluation demonstrates consistent results with our theoretical analysis, and the effectiveness of our proposed design.

关键词： Training Time-frequency analysis Costs Computational modeling Distributed databases Bandwidth Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Faster approximate subgraph counts with privacy 23

Faster approximate subgraph counts with privacy

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Dung Nguyen Mahantesh Halappanavar Venkatesh Srinivasan Anil Vullikanti Department of Computer Science and UVA Biocomplexity Institute and Initiative University of Virginia Data Sciences and Machine Intelligence Group Pacific Northwest National Laboratory Department of Mathematics and Computer Science Santa Clara University

One of the most common problems studied in the context of differential privacy for graph data is counting the number of non-induced embeddings of a subgraph in a given graph. These counts have very high global sensitivity. Therefore, adding noise based on powerful alternative techniques, such as smooth sensitivity and higher-order local sensitivity have been shown to give significantly better accuracy. However, all these alternatives to global sensitivity become computationally very expensive, and to date efficient polynomial time algorithms are known only for few selected subgraphs, such as triangles, k-triangles, and k-stars. In this paper, we show that good approximations to these sensitivity metrics can be still used to get private algorithms. Using this approach, we much faster algorithms for privately counting the number of triangles in real-world social networks, which can be easily parallelized. We also give a private polynomial time algorithm for counting any constant size subgraph using less noise than the global sensitivity; we show this can be improved significantly for counting paths in special classes of graphs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning regularized graphon mean-field games with unknown graphons

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2024年第1期25卷 18217-18311页

作者： Fengzhuo Zhang Vincent Y. F. Tan Zhaoran Wang Zhuoran Yang Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Industrial Engineering and Management Sciences Northwestern University Evanston IL Department of Statistics and Data Science Yale University New Haven CT

We design and analyze reinforcement learning algorithms for Graphon Mean-Field Games (GMFGs). In contrast to previous works that require the precise values of the graphons, we aim to learn the Nash Equilibrium (NE) of the regularized GMFGs when the graphons are unknown. Our contributions are threefold. First, we propose the Proximal Policy Optimization for GMFG (GMFG-PPO) algorithm and show that it converges at a rate of Õ(T1-3) after T iterations with an estimation oracle, improving on a previous work by Xie et al. (ICML, 2021). Second, using kernel embedding of distributions, we design efficient algorithms to estimate the transition kernels, reward functions, and graphons from sampled agents. Convergence rates are then derived when the positions of the agents are either known or unknown. Results for the combination of the optimization algorithm GMFG-PPO and the estimation algorithm are then provided. These algorithms are the first specifically designed for learning graphons from sampled agents. Finally, the efficacy of the proposed algorithms are corroborated through simulations. These simulations demonstrate that learning the unknown graphons reduces the exploitability effectively.

关键词： Graphon mean-field games multi-agent reinforcement learning policy gradient model-based reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Personalized Predictions from Population Level Experiments: A Study on Alzheimer’s Disease

arXiv

引用

arXiv 2024年

作者： Shen, Dennis Agarwal, Anish Misra, Vishal Schelter, Bjoern Shah, Devavrat Shiells, Helen Wischik, Claude USC Department of Data Sciences & Operations United States Columbia University Department of Industrial Engineering & Operations Research United States Columbia University Department of Computer Science United States TauRx Therapeutics United Kingdom MIT Department of Electrical Engineering & Computer Science United States

The purpose of this article is to infer patient level outcomes from population level randomized control trials (RCTs). In this pursuit, we utilize the recently proposed synthetic nearest neighbors (SNN) estimator. At its core, SNN leverages information across patients to impute missing data associated with each patient of interest. We focus on two types of missing data: (i) unrecorded outcomes from discontinuing the assigned treatments and (ii) unobserved outcomes associated with unassigned treatments. data imputation in the former powers and de-biases RCTs, while data imputation in the latter simulates "synthetic RCTs" to predict the outcomes for each patient under every treatment. The SNN estimator is interpretable, transparent, and causally justified under a broad class of missing data scenarios. Relative to several standard methods, we empirically find that SNN performs well for the above two applications using Phase 3 clinical trial data on patients with Alzheimer’s Disease. Our findings directly suggest that SNN can tackle a current pain point within the clinical trial workflow on patient dropouts and serve as a new tool towards the development of precision medicine. Building on our insights, we discuss how SNN can further generalize to real-world applications. Copyright © 2024, The Authors. All rights reserved.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Handy Skin Diseases using Deep Learning to detect Skin Infections While on the Go

Handy Skin Diseases using Deep Learning to detect Skin Infec...

引用

Self Sustainable Artificial Intelligence Systems (ICSSAS), International Conference on

作者： R Saveetha M Nithya S Satheeshkumar M Dakshana K Gunalan P Anandan Department of Computer Technology Bannari Amman Institute of Technology Tamilnadu India Department of Artificial intelligence and data science Bannari Amman Institute of Technology Tamilnadu India Department of Physics Sathyabama Institute of Science and Technology Tamilnadu India

ISBN: (数字)9798350368413

ISBN: (纸本)9798350368420

Skin diseases can significantly impact a person’s quality of life. Accurate and timely diagnosis is crucial for effective treatment. This research explores the application of Convolutional Neural Networks (CNNs) to improve dermatological diagnosis. The study utilizes the ISIC 2017 dataset, a large collection of dermatoscopic images, to train and evaluate various CNN architectures, including VGG-16, AlexNet, DermNet, GoogleNet, and MobileNetV2. Preprocessing techniques are employed to enhance image quality and facilitate accurate classification. The proposed hybrid model, combining DermNet and MobileNet with Softmax and ReLU activation functions, achieves an impressive accuracy of $100 \%$ in classifying skin diseases. This result demonstrates the potential of deep learning techniques to revolutionize dermatological diagnosis, enabling early detection and appropriate treatment.

关键词： Deep learning Training Accuracy Sensitivity Neural networks Skin Convolutional neural networks Reliability Diseases Painting

来源：评论

学校读者我要写书评

暂无评论

Federated PCA and Estimation for Spiked Covariance Matrices: Optimal Rates and Efficient Algorithm

arXiv

引用

arXiv 2024年

作者： Li, Jingyang Cai, T. Tony Xia, Dong Zhang, Anru R. Department of Statistics Department of Mathematics University of Michigan Ann Arbor United States Department of Statistics and Data Science University of Pennsylvania United States Department of Mathematics Hong Kong University of Science and Technology Hong Kong Department of Biostatistics & Bioinformatics Department of Computer Science Duke University United States

Federated Learning (FL) has gained significant recent attention in machine learning for its enhanced privacy and data security, making it indispensable in fields such as healthcare, finance, and personalized services. This paper investigates federated PCA and estimation for spiked covariance matrices under distributed differential privacy constraints. We establish minimax rates of convergence, with a key finding that the central server’s optimal rate is the harmonic mean of the local clients’ minimax rates. This guarantees consistent estimation at the central server as long as at least one local client provides consistent results. Notably, consistency is maintained even if some local estimators are inconsistent, provided there are enough clients. These findings highlight the robustness and scalability of FL for reliable statistical inference under privacy constraints. To establish minimax lower bounds, we derive a matrix version of van Trees’ inequality, which is of independent interest. Furthermore, we propose an efficient algorithm that preserves differential privacy while achieving near-optimal rates at the central server, up to a logarithmic factor. We address significant technical challenges in analyzing this algorithm, which involves a three-layer spectral decomposition. Numerical performance of the proposed algorithm is investigated using both simulated and real data. © 2024, CC BY.

关键词： Federated 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：