检索结果-内蒙古大学图书馆

Fast stochastic ordinal embedding with variance reduction and adaptive step size

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ma, Ke Zeng, Jinshan Xiong, Jiechao Xu, Qianqian Cao, Xiaochun Liu, Wei Yao, Yuan School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China Artificial Intelligence Research Center Peng Cheng Laboratory Shenzhen518055 China School of Computer Information Engineering Jiangxi Normal University NanchangJiangxi330022 China Tencent AI Lab Shenzhen Guangdong China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Cyberspace Security Research Center Peng Cheng Laboratory Shenzhen518055 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China Department of Mathematics and by courtesy Department of Computer Science and Engineering Hong Kong University of Science and Technology Clear Water Bay Kowloon Hong Kong

—Learning representation from relative similarity comparisons, often called ordinal embedding, gains rising attention in recent years. Most of the existing methods are based on semi-definite programming (SDP), which is generally time-consuming and degrades the scalab.lity, especially confronting large-scale data. To overcome this challenge, we propose a stochastic algorithm called SVRG-SBB, which has the following features: i) achieving good scalab.lity via dropping positive semi-definite (PSD) constraints as serving a fast algorithm, i.e., stochastic variance reduced gradient (SVRG) method, and ii) adaptive learning via introducing a new, adaptive step size called the stabilized Barzilai-Borwein (SBB) step size. Theoretically, under some natural assumptions, we show the O(T1 ) rate of convergence to a stationary point of the proposed algorithm, where T is the number of total iterations. Under the further Polyak-Lojasiewicz assumption, we can show the global linear convergence (i.e., exponentially fast converging to a global optimum) of the proposed algorithm. Numerous simulations and real-world data experiments are conducted to show the effectiveness of the proposed algorithm by comparing with the state-of-the-art methods, notably, much lower computational cost with good prediction performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Stochastic systems

A deep learning system for predicting time to progression of diabetic retinopathy

学校读者我要写书评

暂无评论

NATURE MEDICINE 2024年第2期30卷 358-359页

作者： [Anonymous] Shanghai Belt and Road International Joint Laboratory for Intelligent Prevention and Treatment of Metabolic Disorders Department of Computer Science and Engineering School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Department of Endocrinology and Metabolism Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai Diabetes Institute Shanghai Clinical Center for Diabetes Shanghai China MOE Key Laboratory of AI School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Ophthalmology Huadong Sanatorium Wuxi China Department of Ophthalmology Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Ophthalmology and Visual Sciences The Chinese University of Hong Kong Hong Kong China Singapore Eye Research Institute Singapore National Eye Centre Singapore Singapore Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong China Department of Chemical and Biological Engineering The Hong Kong University of Science and Technology Hong Kong China State Key Laboratory of Ophthalmology Zhongshan Ophthalmic Center Sun Yat-sen University Guangdong Provincial Key Laboratory of Ophthalmology and Visual Science Guangzhou China Department of Ophthalmology Peking Union Medical College Hospital Peking Union Medical College Chinese Academy of Medical Sciences Beijing China Medical Records and Statistics Office Shanghai Sixth People’s Hospital Affiliated to Shanghai Jiao Tong University School of Medicine Shanghai China Department of Geriatrics Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China 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 Tech

We developed and validated a deep learning system (termed DeepDR Plus) in a diverse, multiethnic, multi-country dataset to predict personalized risk and time to progression of diabetic retinopathy. We show that DeepDR Plus can be integrated into the clinical workflow to promote individualized intervention strategies for the management of diabetic retinopathy.

关键词： Diabetes complications Machine learning Predictive markers

Ppdrm: Privacy-Preserving Drm Training and Classification on the Cloud

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Xu, Lida Tian, Chengliang Zhang, Guoyan Li, Leibo Tian, Weizhong Zhang, Yan College of Computer Science and Technology Qingdao University Qingdao266071 China School of Cyber Science and Technology Shandong University Shandong Ji’nan250101 China Key Laboratory of Cryptologic Technology and Information Security Ministry of Education Shandong Ji’nan250101 China Shandong Institute of Blockchain Shandong Ji’nan250101 China College of Big Data and Internet Shenzhen Technology University Guangdong Shenzhen518118 China College of Electromechanical Engineering Qingdao University of Science and Technology Qingdao266061 China

The prevalence of cloud computing greatly promotes the development of artificial intelligence(AI). Accurately and efficiently classify data on the cloud is a classic AI task. The recent Discriminative Ridge Machine(DRM) is a new type of supervised classifier which outperforms many other classic classifiers in accuracy and efficiency, especially for high-dimensional data or unbalanced ***, the DRM training and classification task is tedious for resource-constrained data owners. Motivated by this, in this paper, we study the outsourcing of DRM training and classification within a cloud environment and propose a quantum secure and efficient solution for this problem. Specifically, based on the two non-colluding servers model, we adopt the quantum-immune CKKS cryptosystem to design a series of homomorphic security protocols for matrix and argmin operations and realize the correct model training and data classification without leaking the privacy of training dataset, the DRM model, the query data and the classification results. We argue the $\mathcal{CPA}$ secure of our design and evaluate the accuracy and efficiency from theory and experiment perspectives. Our theoretical and experimental analysis demonstrates that our design can achieve the same classification accuracy as the origin plaintext-based DRM classifier and the query-response time is reasonable and acceptable. © 2023, The Authors. All rights reserved.

关键词： Classification (of information)

CRS-Diff: Controllab.e Remote Sensing Image Generation with Diffusion Model

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, datao Cao, Xiangyong Hou, Xingsong Jiang, Zhongyuan Liu, Junmin Meng, Deyu The School of Computer Science and Technology the Ministry of Education Key Lab for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an710049 China The School of Information and Communications Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China The School of Cyber Engineering Xidian University Shaanxi Xi’an710049 China The School of Mathematics and Statistics the Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University Shaanxi Xi’an710049 China Guangdong Guangzhou510555 China

The emergence of generative models has revolutionized the field of remote sensing (RS) image generation. Despite generating high-quality images, existing methods are limited in relying mainly on text control conditions, and thus do not always generate images accurately and stably. In this paper, we propose CRS-Diff, a new RS generative framework specifically tailored for RS image generation, leveraging the inherent advantages of diffusion models while integrating more advanced control mechanisms. Specifically, CRS-Diff can simultaneously support text-condition, metadata-condition, and image-condition control inputs, thus enabling more precise control to refine the generation process. To effectively integrate multiple condition control information, we introduce a new conditional control mechanism to achieve multi-scale feature fusion, thus enhancing the guiding effect of control conditions. To our knowledge, CRS-Diff is the first multiple-condition controllab.e RS generative model. Experimental results in single-condition and multiple-condition cases have demonstrated the superior ability of our CRS-Diff to generate RS images both quantitatively and qualitatively compared with previous methods. Additionally, our CRS-Diff can serve as a data engine that generates high-quality training data for downstream tasks, e.g., road extraction. The code is availab.e at https://***/Sonettoo/CRS-Diff. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

PR-PL: A Novel Transfer Learning Framework with Prototypical Representation based Pairwise Learning for EEG-Based Emotion Recognition

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Rushuang Zhang, Zhiguo Fu, Hong Zhang, Li Li, Linling Huang, Gan Dong, Yining Li, Fali Yang, Xin Jane, Zhen Liang School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Biomedical Measurements and Ultrasound Imaging Shenzhen China School of Computer Science and Technology Harbin Insti- tute of Technology Shenzhen China Marshall Laboratory of Biomedical Engineering Shenzhen China Peng Cheng Laboratory Shenzhen China Department of Mathematics and Information Technology The Education University of Hong Kong Hong Kong School of Data Science City University of Hong Kong Hong Kong The Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation University of Electronic Science and Technology of China China School of Life Science and Technology Center for Information in Medicine University of Electronic Science and Technology of China China

Affective brain-computer interfaces based on electroencephalography (EEG) is an important branch in the field of affective computing. However, individual differences and noisy lab.ls seriously limit the effectiveness and generalizability of EEG-based emotion recognition models. In this paper, we propose a novel transfer learning framework with Prototypical Representation based Pairwise Learning (PR-PL) to learn discriminative and generalized prototypical representations for emotion revealing across individuals and formulate emotion recognition as pairwise learning for alleviating the reliance on precise lab.l information. More specifically, a prototypical learning-based adversarial discriminative domain adaptation method is developed to encode the inherent emotion-related semantic structure of EEG data, while pairwise learning with an adaptive pseudo-lab.ling method is developed to achieve a reliable and stable model learning with noisy lab.ls. Through domain adaptation, feature representations of source and target domains are aligned on a shared feature space, while the feature separability of both source and target domains is also considered. The characterized prototypical representations are evident with a high feature concentration within one single emotion category and a high feature separability across different emotion categories. Extensive experiments are conducted on two benchmark databases under four cross-validation evaluation protocols (cross-subject cross-session, cross-subject within-session, within-subject cross-session, and within-subject within-session). The experimental results demonstrate the superiority of the proposed PR-PL against the state-of-the-arts under all four evaluation protocols, which shows the effectiveness and generalizability of PR-PL in dealing with the ambiguity of EEG responses in affective studies. The source code is availab.e at https://***/KAZABANA/PR-PL. Copyright © 2022, The Authors. All rights reserved.

关键词： Electrophysiology

Towards Unified Token Learning for Vision-Language Tracking

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, Xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

A Double Auction for Charging Scheduling among Vehicles Using DAG-Blockchains

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Guo, Jianxiong Ding, Xingjian Wu, Weili Du, Ding-Zhu Advanced Institute of Natural Sciences Beijing Normal University Zhuhai519087 China Guangdong Key Lab of AI and Multi-Modal Data Processing BNU-HKBU United International College Zhuhai519087 China Faculty of Information Technology Beijing University of Technology Beijing100124 China Department of Computer Science Erik Jonsson School of Engineering and Computer Science The University of Texas at Dallas RichardsonTX75080 United States

Electric Vehicles (EVs) are becoming more and more popular in our daily life, which replaces traditional fuel vehicles to reduce carbon emissions and protect the environment. EVs need to be charged, but the number of charging piles in a Charging Station (CS) is limited and charging is usually more time-consuming than fueling. According to this scenario, we propose a secure and efficient charging scheduling system based on a Directed Acyclic Graph (DAG)-blockchain and double auction mechanism. In a smart area, it attempts to assign EVs to the availab.e CSs in the light of their submitted charging requests and status information. First, we design a lightweight charging scheduling framework that integrates DAG-blockchain and modern cryptography technology to ensure security and scalab.lity during performing scheduling and completing tradings. In this process, a constrained multi-item double auction problem is formulated because of the limited charging resources in a CS, which motivates EVs and CSs in this area to participate in the market based on their preferences and statuses. Due to this constraint, our problem is more complicated and harder to achieve truthfulness as well as system efficiency compared to the existing double auction model. To adapt to it, we propose two algorithms, namely Truthful Mechanism for Charging (TMC) and Efficient Mechanism for Charging (EMC), to determine an assignment between EVs and CSs and pricing strategies. Then, both theoretical analysis and numerical simulations show the correctness and effectiveness of our proposed algorithms. Copyright © 2020, The Authors. All rights reserved.

关键词： Blockchain

DONet: Dual-octave network for fast MR image reconstruction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Feng, Chun-Mei Yang, Zhanyuan Fu, Huazhu Xu, Yong Yang, Jian Shao, Ling Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen518055 China School of Automation Engineering University of Electronic Science and Technology of China 611731 China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates PCA Laboratory Key Lab. of Intelligent Percept. and Syst. for High-Dimensional Information of Ministry of Education Nanjiang University of Science and Technology Nanjiang210094 China Jiangsu Key Laboratory of Image and Video Understanding for Social Security School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China

Magnetic resonance (MR) image acquisition is an inherently prolonged process, whose acceleration has long been the subject of research. This is commonly achieved by obtaining multiple undersampled images, simultaneously, through parallel imaging. In this paper, we propose the Dual-Octave Network (DONet), which is capable of learning multi-scale spatialfrequency features from both the real and imaginary components of MR data, for parallel fast MR image reconstruction. More specifically, our DONet consists of a series of Dual-Octave convolutions (Dual-OctConv), which are connected in a dense manner for better reuse of features. In each Dual-OctConv, the input feature maps and convolutional kernels are first split into two components (i.e., real and imaginary), and then divided into four groups according to their spatial frequencies. Then, our Dual-OctConv conducts intra-group information updating and inter-group information exchange to aggregate the contextual information across different groups. Our framework provides three appealing benefits: (i) It encourages information interaction and fusion between the real and imaginary components at various spatial frequencies to achieve richer representational capacity. (ii) The dense connections between the real and imaginary groups in each Dual-OctConv make the propagation of features more efficient by feature reuse. (iii) DONet enlarges the receptive field by learning multiple spatial-frequency features of both the real and imaginary components. Extensive experiments on two popular datasets (i.e., clinical knee and fastMRI), under different undersampling patterns and acceleration factors, demonstrate the superiority of our model in accelerated parallel MR image reconstruction. © 2021, CC BY.

关键词： Magnetic resonance imaging

Deep User Modeling for Content-based Event Recommendation in Event-based Social Networks

学校读者我要写书评

暂无评论

Deep User Modeling for Content-based Event Recommendation in...

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

作者： Zhibo Wang Yongquan Zhang Honglong Chen Zhetao Li Feng Xia Jiangsu Key Lab. of Big Data Security & Intelligent Processing NJUPT P. R. China School of Cyber Science and Engineering Wuhan University P. R. China College of Information and Control Engineering China University of Petroleum P. R. China College of Information Engineering Xiangtan University P. R. China School of Software Dalian University of Technology P. R. China

ISBN: (纸本)9781538641293

Event-based social networks (EBSNs) are the newly emerging social platforms for users to publish events online and attract others to attend events offline. The content information of events plays an important role in event recommendation. However, the content-based approaches in existing event recommender systems cannot fully represent the preference of each user on events since most of them focus on exploiting the content information from events' perspective, and the bag-of-words model, commonly used by them, can only capture word frequency but ignore word orders and sentence structure. In this paper, we shift the focus from events' perspective to users' perspective, and propose a Deep User Modeling framework for Event Recommendation (DUMER) to characterize the preference of users by exploiting the contextual information of events that users have attended. Specifically, we utilize convolutional neural network (CNN) with word embedding to deeply capture the contextual information of a user's interested events and build up a user latent model for each user. We then incorporate the user latent model into probabilistic matrix factorization (PMF) model to enhance the recommendation accuracy. We conduct experiments on the real-world dataset crawled from a typical EBSN, ***, and the experimental results show that DUMER outperforms the compared benchmarks.

关键词： Recommender systems Machine learning Social network services Feature extraction Context modeling Conferences Probabilistic logic