检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Yue He Dongbai Li Pengfei Tian Han Yu Jiashuo Liu Hao Zou Peng Cui Department of Computer Science and Technology Tsinghua University Beijing China Qiuzhen College Tsinghua University Beijing China Zhongguancun Laboratory Beijing China

Despite notable progress in enhancing the capability of machine learning against distribution shifts, training data quality remains a bottleneck for cross-distribution generalization. Recently, from a data-centric perspective, there have been considerable efforts to improve model performance through refining the preparation of training data. Inspired by realistic scenarios, this paper addresses a practical requirement of acquiring training samples from various domains on a limited budget to facilitate model generalization to target test domain with distribution shift. Our empirical evidence indicates that the advance in data acquisition can significantly benefit the model performance on shifted data. Additionally, by leveraging unlabeled test domain data, we introduce a Domain-wise Active Acquisition framework. This framework iteratively optimizes the data acquisition strategy as training samples are accumulated, theoretically ensuring the effective approximation of test distribution. Extensive real-world experiments demonstrate our proposal's advantages in machine learning applications. The code is available at https://***/dongbaili/DAA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Matrix Factorization for Inferring Associations and Missing Links

arXiv

引用

arXiv 2025年

作者： Barron, Ryan Eren, Maksim E. Truong, Duc P. Matuszek, Cynthia Wendelberger, James Dorn, Mary F. Alexandrov, Boian Theoretical Division Los Alamos National Laboratory United States Information Systems and Modeling Los Alamos National Laboratory United States Department of Computer Science and Electrical Engineering University of Maryland Baltimore County United States Computer Computational and Statistical Sciences Los Alamos National Laboratory United States

Missing link prediction is a method for network analysis, with applications in recommender systems, biology, social sciences, cybersecurity, information retrieval, and Artificial Intelligence (AI) reasoning in Knowledge Graphs. Missing link prediction identifies unseen but potentially existing connections in a network by analyzing the observed patterns and relationships. In proliferation detection, this supports efforts to identify and characterize attempts by state and non-state actors to acquire nuclear weapons or associated technology - a notoriously challenging but vital mission for global security. Dimensionality reduction techniques like Non-Negative Matrix Factorization (NMF) and Logistic Matrix Factorization (LMF) are effective but require selection of the matrix rank parameter, that is, of the number of hidden features, k, to avoid over/under-fitting. We introduce novel Weighted (WNMFk), Boolean (BNMFk), and Recommender (RNMFk) matrix factorization methods, along with ensemble variants incorporating logistic factorization, for link prediction. Our methods integrate automatic model determination for rank estimation by evaluating stability and accuracy using a modified bootstrap methodology and uncertainty quantification (UQ), assessing prediction reliability under random perturbations. Additionally, we incorporate Otsu threshold selection and k-means clustering for Boolean matrix factorization, comparing them to coordinate descent-based Boolean thresholding. Our experiments highlight the impact of rank k selection, evaluate model performance under varying test-set sizes, and demonstrate the benefits of UQ for reliable predictions using abstention. We validate our methods on three synthetic datasets (Boolean and Gaussian distributed) and benchmark them against LMF and symmetric LMF (symLMF) on five real-world protein-protein interaction networks, showcasing an improved prediction performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Learning on Graphs under Label Noise

Learning on Graphs under Label Noise

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Jingyang Yuan Xiao Luo Yifang Qin Yusheng Zhao Wei Ju Ming Zhang National Key Laboratory for Multimedia Information Processing Peking University Beijing China School of Computer Science Peking University Beijing China Department of Computer Science University of California Los Angeles USA

Node classification on graphs is a significant task with a wide range of applications, including social analysis and anomaly detection. Even though graph neural networks (GNNs) have produced promising results on this task, current techniques often presume that label information of nodes is accurate, which may not be the case in real-world applications. To tackle this issue, we investigate the problem of learning on graphs with label noise and develop a novel approach dubbed Consistent Graph Neural Network (CGNN) to solve it. Specifically, we employ graph contrastive learning as a regularization term, which promotes two views of augmented nodes to have consistent representations. Since this regularization term cannot utilize label information, it can enhance the robustness of node representations to label noise. Moreover, to detect noisy labels on the graph, we present a sample selection technique based on the homophily assumption, which identifies noisy nodes by measuring the consistency between the labels with their neighbors. Finally, we purify these confident noisy labels to permit efficient semantic graph learning. Extensive experiments on three well-known benchmark datasets demonstrate the superiority of our CGNN over competing approaches.

关键词： Semantics Benchmark testing Signal processing Graph neural networks Robustness Acoustics Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Combining Deep Learning Models for Cytological Image Classification

Combining Deep Learning Models for Cytological Image Classif...

引用

African Federation of Operational Research Societies (AFROS), International Conference of the

作者： Mohammed Lamine Benomar Traoré Alimata Guindo Sadio University of Ain Temouchent Biomedical Engineering Laboratory University of Tlemcen Algeria Computer science department University of Ain Temouchent Ain Temouchent Algeria

ISBN: (数字)9798350386448

ISBN: (纸本)9798350386455

The classification of medical images has greatly advanced due to improvements in imaging technologies and the application of deep learning. This study presents an automatic system for classifying peripheral blood cells, leveraging deep learning and transfer learning techniques to enhance performance and efficiency. We developed three designs combining convolutional architectures: VGG16, InceptionV3and ResNet50. The first design combines VGG16 and InceptionV3, the second concatenates InceptionV3and ResNet50, and the third associates VGG16 and ResNet50. Experiments were conducted on the Peripheral Blood Cell (PBC) dataset, containing 17,092 images across eight distinct classes. The results demonstrate the effectiveness of our approach, achieving a maximum accuracy of 99%.

关键词： Deep learning Accuracy Transfer learning Cells (biology) computer architecture Transformers Blood Residual neural networks Load modeling Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Information Bottleneck Attribution Based Retinal Disease Classification Using OCT Images 8th

Information Bottleneck Attribution Based Retinal Disease Cla...

引用

8th International Conference on Signal and Information Processing, Network and computers, ICSINC 2021

作者： Aslam, Sehrish Zheng, Yuanjie Li, Xiaojie Wang, Junxia Ullah, Muhammad Zakir Kaizolu, Gogo Dauda Gohar, Neelam School of Information Science and Engineering Shandong Normal University Jinan250358 China Shandong Provincial Key Laboratory of Higher Education School of Information Science and Engineering Life and Health Research Institute Shandong Normal University Jinan250358 China Department of Computer Science Shaheed Benazir Bhutto Women University Peshawar Pakistan

ISBN: (纸本)9789811933868

The existence of deep learning’s "black box" makes it difficult to understand how the algorithms analyze patterns and make image-level predictions. A representation of the pixels contributing the most to the algorithm’s classification will require new insights. Classification methods for neurodegenerative ocular disorders have been developed using machine learning and image processing techniques with considerable efficacy. However, the techniques’ robustness and transferability remain uncertain. We have developed a new classification method based upon information bottleneck to analyze the attribution of each feature and the information provided for the network prediction in each input area for a clear understanding of the affectability of a black-box model. In this research, we apply the attribution information bottleneck and limit the information flow and assess the amount of information image areas produce in bits by allowing noise to intermediate feature maps. Our studies indicate that the information bottleneck for attribution (IBA) has increased model interpretability and gives a more reliable estimation through a publicly available dataset. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

The Coming Wave of Aquatic Robotics

引用

Resource: Engineering and Technology for Sustainable World 2022年第4期29卷 12-13页

作者： Young, Sierra Ore, John-Paul Hall, Steven P.E. Utah Water Research Laboratory Utah State University Logan United States Department of Computer Science North Carolina State University Raleigh United States Marine Aquaculture Research Center North Carolina State University Raleigh United States

Behind the scenes, local municipalities and environmental agencies conduct the water testing needed to ensure public safety. While this is a critical service, it can also be resource-intensive and timeconsuming, as many programs rely on manual sampling and data collection. This can mean that some water bodies are sampled only once a year, or even less.

关键词： Aquatic robotics Collaborative robots Monitoring water quality Robotic Sampling Unoccupied surface vehicles USV technology Water resources

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Approach for Detecting Colorectal Cancer via Raman Spectra

引用

Biomedical Engineering Frontiers 2022年第1期3卷 149-158页

作者： Zheng Cao Xiang Pan Hongyun Yu Shiyuan Hua Da Wang Danny Z.Chen Min Zhou Jian Wu RealDoctor AI Research Center College of Computer Science and TechnologyZhejiang UniversityChina Key Laboratory of Cancer Prevention and Intervention Ministry of EducationThe Second Affiliated HospitalZhejiang University School of MedicineChina Institute of Translational Medicine and the Cancer Institute of the Second Affiliated Hospital Zhejiang University School of MedicineChina Department of Computer Science and Engineering University of Notre DameUSA Second Affiliated Hospital School of Medicine and School of Public HealthZhejiang UniversityChina

Objective and Impact *** tumors from normal tissues is vital in the intraoperative diagnosis and pathological *** this work,we propose to utilize Raman spectroscopy as a novel modality in surgery to detect colorectal cancer *** spectra can reflect the substance components of the target ***,the feature peak is slight and hard to detect due to environmental *** a high-quality Raman spectroscopy dataset and developing effective deep learning detection methods are possibly viable ***,we collect a large Raman spectroscopy dataset from 26 colorectal cancer patients with the Raman shift ranging from 385 to 1545 cm^(−1).Second,a one-dimensional residual convolutional neural network(1D-ResNet)architecture is designed to classify the tumor tissues of colorectal ***,we visualize and interpret the fingerprint peaks found by our deep learning *** results show that our deep learning method achieves 98.5%accuracy in the detection of colorectal cancer and outperforms traditional ***,Raman spectra are a novel modality for clinical detection of colorectal *** proposed ensemble 1D-ResNet could effectively classify the Raman spectra obtained from colorectal tumor tissues or normal tissues.

关键词： colorectal viable modality

来源：评论

学校读者我要写书评

暂无评论

DFCP: Few-Shot DeepFake Detection via Contrastive Pretraining

DFCP: Few-Shot DeepFake Detection via Contrastive Pretrainin...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Bo Zou Chao Yang Jiazhi Guan Chengbin Quan Youjian Zhao Department of Computer Science and Technology Tsinghua University Beijing China Shanghai AI Laboratory Shanghai China Zhongguancun Laboratory Beijing China

Abuses of forgery techniques have created a considerable problem of misinformation on social media. Although scholars devote many efforts to face forgery detection (a.k.a DeepFake detection) and achieve some results, two issues still hinder the practical application. 1) Most detectors do not generalize well to unseen datasets. 2) In a supervised manner, most previous works require a considerable amount of manually labeled data. To address these problems, we propose a simple contrastive pertaining framework for DeepFake detection (DFCP), which works in a finetuning-after-pretraining manner, and requires only a few labels (5%). Specifically, we design a two-stream framework to simultaneously learn high-frequency texture features and high-level semantics information during pretraining. In addition, a video-based frame sampling strategy is proposed to mitigate potential noise data in the instance-discriminative contrastive learning to achieve better performance. Experimental results on several downstream datasets show the state-of-the-art performance of the proposed DFCP, which works at frame-level (w/o temporal reasoning) with high efficiency but outperforms video-level methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LEARNING OUTFIT COMPATIBILITY WITH GRAPH ATTENTION NETWORK AND VISUAL-SEMANTIC EMBEDDING

LEARNING OUTFIT COMPATIBILITY WITH GRAPH ATTENTION NETWORK A...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Wang, Jianfeng Cheng, Xiaochun Wang, Ruomei Liu, Shaohui School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Department of Computer Science Middlesex University London United Kingdom School of Computer Science and Technology Harbin Institute of Technology Harbin China Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9781665438643

Fashion recommendation is an essential component of user shopping that it is capable of selecting and presenting fascinating items to customers. The fact that humans exhibit inconsistencies for fashion items in their choice is known to all due to the visual aesthetic features and fine-grained differences of fashion items. Previous research on fashion recommendations mainly focuses on sequential models, most of them only consider complex similarity relationships in fashion compatibility while neglecting the real-world compatible information often desired in practical applications. To learn the fashion compatibility and generate for the outfit, we propose an approach that jointly learns latent fashion concepts in visual-semantic space to measure compatibility between items. The fashion concepts are shaped by design elements such as color, material, and silhouette. Accordingly, we model a unified representation to learn different notions of similarity by mapping text descriptors and images into latent space to learn high-level representations. Experimental results reveal that our method effectively reaches the aimed results on the fill-in-the-blank and outfit compatibility tasks. © 2021 IEEE

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

LinSATNet: The Positive Linear Satisfiability Neural Networks

arXiv

引用

arXiv 2024年

作者： Wang, Runzhong Zhang, Yunhao Guo, Ziao Chen, Tianyi Yang, Xiaokang Yan, Junchi Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China Shanghai AI Laboratory China

Encoding constraints into neural networks is attractive. This paper studies how to introduce the popular positive linear satisfiability to neural networks. We propose the first differentiable satisfiability layer based on an extension of the classic Sinkhorn algorithm for jointly encoding multiple sets of marginal distributions. We further theoretically characterize the convergence property of the Sinkhorn algorithm for multiple marginals. In contrast to the sequential decision e.g. reinforcement learning-based solvers, we showcase our technique in solving constrained (specifically satisfiability) problems by one-shot neural networks, including i) a neural routing solver learned without supervision of optimal solutions;ii) a partial graph matching network handling graphs with unmatchable outliers on both sides;iii) a predictive network for financial portfolios with continuous constraints. To our knowledge, there exists no one-shot neural solver for these scenarios when they are formulated as satisfiability problems. Source code is available at https://***/Thinklab-SJTU/LinSATNet. © 2024, CC BY.

关键词： Encoding (symbols)

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：