检索结果-内蒙古大学图书馆

Evaluating Interpolation and Extrapolation Performance of Neural Retrieval Models

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhan, Jingtao Xie, Xiaohui Mao, Jiaxin Liu, Yiqun Guo, Jiafeng Zhang, Min Ma, Shaoping Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing100084 China Beijing Key Laboratory of Big Data Management and Analysis Methods Gaoling School of Artificial Intelligence Renmin University of China Beijing100872 China CAS Key Lab of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

A retrieval model should not only interpolate the training data but also extrapolate well to the queries that are different from the training data. While neural retrieval models have demonstrated impressive performance on ad-hoc search benchmarks, we still know little about how they perform in terms of interpolation and extrapolation. In this paper, we demonstrate the importance of separately evaluating the two capabilities of neural retrieval models. Firstly, we examine existing ad-hoc search benchmarks from the two perspectives. We investigate the distribution of training and test data and find a considerable overlap in query entities, query intent, and relevance labels. This finding implies that the evaluation on these test sets is biased toward interpolation and cannot accurately reflect the extrapolation capacity. Secondly, we propose a novel evaluation protocol to separately evaluate the interpolation and extrapolation performance on existing benchmark datasets. It resamples the training and test data based on query similarity and utilizes the resampled dataset for training and evaluation. Finally, we leverage the proposed evaluation protocol to comprehensively revisit a number of widely-adopted neural retrieval models. Results show models perform differently when moving from interpolation to extrapolation. For example, representation-based retrieval models perform almost as well as interaction-based retrieval models in terms of interpolation but not extrapolation. Therefore, it is necessary to separately evaluate both interpolation and extrapolation performance and the proposed resampling method serves as a simple yet effective evaluation tool for future IR studies. Copyright © 2022, The Authors. All rights reserved.

关键词： Extrapolation

AID-DTI: ACCELERATING HIGH-FIDELITY DIFFUSION TENSOR IMAGING WITH DETAIL-PRESERVING MODEL-BASED DEEP LEARNING

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fan, Wenxin Cheng, Jian Li, Cheng Ma, Xinrui Yang, Jing Zou, Juan Wu, Ruoyou Liu, Qiegen Wang, Shanshan Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Peng Cheng Laboratory Guangdong Shenzhen China Nan Chang University Jiang Xi Nan Chang China

Deep learning has shown great potential in accelerating diffusion tensor imaging (DTI). Nevertheless, existing methods tend to suffer from Rician noise and detail loss in reconstructing the DTI-derived parametric maps especially when sparsely sampled q-space data are used. This paper proposes a novel method, AID-DTI (Accelerating hIgh fiDelity Diffusion Tensor Imaging), to facilitate fast and accurate DTI with only six measurements. AID-DTI is equipped with a newly designed Singular Value Decomposition (SVD)-based regularizer, which can effectively capture fine details while suppressing noise during network training. Experimental results on Human Connectome Project (HCP) data consistently demonstrate that the proposed method estimates DTI parameter maps with fine-grained details and outperforms three state-of-the-art methods both quantitatively and qualitatively. Copyright © 2024, The Authors. All rights reserved.

关键词： Singular value decomposition

Dual-View Pyramid Pooling in Deep Neural Networks for Improved Medical Image Classification and Confidence Calibration

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Xiaoqing Nie, Qiushi Xiao, Zunjie Zhao, Jilu Wu, Xiao Guo, Pengxin Li, Runzhi Liu, Jin Wei, Yanjie Pan, Yi Center for High Performance Computing Shenzhen Key Laboratory of Intelligent Bioinformatics Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen518055 China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Department of Statistics and Actuarial Science The University of Hong Kong 999077 Hong Kong Cooperative Innovation Center of Internet Healthcare Zhengzhou University Zhengzhou450001 China Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi830046 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China

Spatial pooling (SP) and cross-channel pooling (CCP) operators have been applied to aggregate spatial features and pixel-wise features from feature maps in deep neural networks (DNNs), respectively. Their main goal is to reduce computation and memory overhead without visibly weakening the performance of DNNs. However, SP often faces the problem of losing the subtle feature representations, while CCP has a high possibility of ignoring salient feature representations, which may lead to both miscalibration of confidence issues and suboptimal medical classification results. To address these problems, we propose a novel dual-view framework, the first to systematically investigate the relative roles of SP and CCP by analyzing the difference between spatial features and pixel-wise features. Based on this framework, we propose a new pooling method, termed dual-view pyramid pooling (DVPP), to aggregate multi-scale dual-view features. DVPP aims to boost both medical image classification and confidence calibration performance by fully leveraging the merits of SP and CCP operators from a dual-axis perspective. Additionally, we discuss how to fulfill DVPP with five parameter-free implementations. Extensive experiments on six 2D/3D medical image classification tasks show that our DVPP surpasses state-of-the-art pooling methods in terms of medical image classification results and confidence calibration across different DNNs. © 2024, CC BY.

关键词： Deep neural networks

GSLB: The Graph Structure Learning Benchmark 37

学校读者我要写书评

暂无评论

GSLB: The Graph Structure Learning Benchmark

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Li, Zhixun Wang, Liang Sun, Xin Luo, Yifan Zhu, Yanqiao Chen, Dingshuo Luo, Yingtao Zhou, Xiangxin Liu, Qiang Wu, Shu Yu, Jeffrey Xu Department of Systems Engineering and Engineering Management The Chinese University of Hong Kong Hong Kong Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China Department of Automation University of Science and Technology of China China School of Cyberspace Security Beijing University of Posts and Telecommunications China Department of Computer Science University of California Los Angeles United States Heinz College of Information Systems and Public Policy Machine Learning Department School of Computer Science Carnegie Mellon University United States

ISBN: (纸本)9781713899921

Graph Structure Learning (GSL) has recently garnered considerable attention due to its ability to optimize both the parameters of Graph Neural Networks (GNNs) and the computation graph structure simultaneously. Despite the proliferation of GSL methods developed in recent years, there is no standard experimental setting or fair comparison for performance evaluation, which creates a great obstacle to understanding the progress in this field. To fill this gap, we systematically analyze the performance of GSL in different scenarios and develop a comprehensive Graph Structure Learning Benchmark (GSLB) curated from 20 diverse graph datasets and 16 distinct GSL algorithms. Specifically, GSLB systematically investigates the characteristics of GSL in terms of three dimensions: effectiveness, robustness, and complexity. We comprehensively evaluate state-of-the-art GSL algorithms in node- and graph-level tasks, and analyze their performance in robust learning and model complexity. Further, to facilitate reproducible research, we have developed an easy-to-use library for training, evaluating, and visualizing different GSL methods. Empirical results of our extensive experiments demonstrate the ability of GSL and reveal its potential benefits on various downstream tasks, offering insights and opportunities for future research. The code of GSLB is available at: https://***/GSL-Benchmark/GSLB. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Graphic methods

Programming Variational Quantum Circuits with Quantum-Train Agent

学校读者我要写书评

暂无评论

Programming Variational Quantum Circuits with Quantum-Train ...

Quantum Communications, Networking, and computing (QCNC), International Conference on

作者： Chen-Yu Liu Samuel Yen-Chi Chen Kuan-Cheng Chen Wei-Jia Huang Yen-Jui Chang Graduate Institute of Applied Physics National Taiwan University Taipei Taiwan Hon Hai (Foxconn) Research Institute Taipei Taiwan Wells Fargo New York NY USA Department of Electrical and Electronic Engineering Imperial College London London UK Centre for Quantum Engineering Science and Technology (QuEST) Imperial College London London UK Quantum Information Center Chung Yuan Christian University Taoyuan City Taiwan Master Program in Intelligent Computing and Big Data Chung Yuan Christian University Taoyuan City Taiwan

ISBN: (数字)9798331531591

ISBN: (纸本)9798331531607

This study introduces the Quantum-Train Quantum Fast Weight Programmer (QT-QFWP) framework, enabling efficient and scalable programming of variational quantum circuits (VQCs) through quantum-driven parameter updates for the classical slow programmer controlling the fast programmer VQC. By optimizing quantum and classical parameter management, QT-QFWP significantly reduces parameters (by 70–90%) compared to Quantum Long Short-Term Memory (QLSTM) and Quantum Fast Weight Programmer (QFWP) while maintaining accuracy. Benchmarking on time-series tasks—including Damped Simple Harmonic Motion (SHM), NARMA5, and Simulated Gravitational Waves (GW)—demonstrates superior efficiency and predictive accuracy. QT-QFWP is particularly advantageous for near-term quantum systems, addressing qubit and gate fidelity constraints, enhancing VQC deployment in time-sensitive applications, and expanding quantum computing’s role in machine learning.

关键词： Quantum system Accuracy Computational modeling Qubit Neural networks Programming Predictive models Quantum circuit Physics Long short term memory

Federated Learning for Medical Image Classification: Advances, Challenges and Opportunities

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zhang, Xiaobo Zhao, Xiaole Wu, Yunyang Zheng, Hailong Li, Yang School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu611756 China Artificial Intelligence Research Institute Southwest Jiaotong University Chengdu611756 China National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China

Medical images are private integrations comprising private patient information owned by various hospitals and relevant research institutes, and the generated image data can be utilized to infer physical health conditions. In recent years, more and more AI researchers have used medical images as datasets for their analysis purposes, which will cause relevant personnel to worry about their privacy. As a distributed machine learning framework, federated learning can effectively solve the problem of data privacy. It participates in and completes model training without sharing personal data, with strong universality and good results. In this work, Computed Tomography (CT), Magnetic Resonance Imaging (MRI), Wilhelm Conrad Röntgen (X-Ray) as well as other typical medical imaging modes are used as research objects to summarize, analyze and look forward to the previous work related to federal learning in the field of medical image analysis. On the one hand, this survey classifies and compares the existing federal learning framework and algorithm for different medical image datasets;on the other hand, it discusses the relevant federal studies that are widely used in medical images, analyses the problems that need to be solved in the field of medical images, and looks forward to future studies. © 2023, The Authors. All rights reserved.

关键词： Medical imaging

3D ANATOMICAL STRUCTURE-GUIDED DEEP LEARNING FOR ACCURATE DIFFUSION MICROSTRUCTURE IMAGING

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ma, Xinrui Cheng, Jian Fan, Wenxin Wu, Ruoyou Ye, Yongquan Wang, Shanshan Paul C. Lauterbur Research Center for Biomedical Imaging Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Guangdong Shenzhen China University of Chinese Academy of Sciences Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Key Laboratory of Data Science and Intelligent Computing Institute of International Innovation Beihang University Zhejiang Hangzhou China Pengcheng Laboratory Guangdong Shenzhen China United Imaging Healthcare HoustonTX United States

Diffusion magnetic resonance imaging (dMRI) is a crucial noninvasive technique for exploring the microstructure of the living human brain. Traditional hand-crafted and model-based tissue microstructure reconstruction methods often require extensive diffusion gradient sampling, which can be time-consuming and limits the clinical applicability of tissue microstructure information. Recent advances in deep learning have shown promise in microstructure estimation;however, accurately estimating tissue microstructure from clinically feasible dMRI scans remains challenging without appropriate constraints. This paper introduces a novel framework that achieves high-fidelity and rapid diffusion microstructure imaging by simultaneously leveraging anatomical information from macro-level priors and mutual information across parameters. This approach enhances time efficiency while maintaining accuracy in microstructure estimation. Experimental results demonstrate that our method outperforms four state-of-the-art techniques, achieving a peak signal-to-noise ratio (PSNR) of 30.51±0.58 and a structural similarity index measure (SSIM) of 0.97±0.004 in estimating parametric maps of multiple diffusion models. Notably, our method achieves a 15× acceleration compared to the dense sampling approach, which typically utilizes 270 diffusion gradients. © 2025, CC BY-NC-ND.

关键词： Tissue

Driving Behavior Safety Assessment in Edge computing Using Multitask Discriminative TS Fuzzy Model

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2024年

作者： Gu, Yi Chen, Zhiyu Wang, Lu Shen, Jinsong Bashir, Ali Kashif Wang, Wei Jiangnan University School of Artificial Intelligence and Computer Science Wuxi214122 China Jiangnan University Engineering Research Center of Intelligent Technology for Healthcare Ministry of Education Wuxi214122 China Chongqing University School of Big Data and Software Engineering Chongqing400044 China Jiangsu Keli Internet Information Technology Co. Ltd Jingjiang214500 China Manchester Metropolitan University Department of Computing and Mathematics United Kingdom Woxsen University Woxsen School of Business Hyderabad502 345 India Lebanese American University Department of Computer Science and Mathematics Beirut Lebanon Shenzhen MSU-BIT University Artificial Intelligence Research Institute Shenzhen518172 China

Driving behavior safety analysis in edge computing involves the real-time collection and processing of vehicle driving data. Fuzzy models have advantages in analyzing driving behavior due to their excellent ability to handle uncertain information. This study develops a multitask discriminative Takagi-Sugeno fuzzy model (MD-TS-FM) for driving behavior safety assessment. To comprehensively analyze the correlation and differences in multitask driving behaviors, the designed consequent part consists of two parts: task-shared part reflects the shared intrinsic structure information that are consistent across different driving tasks, and task-specific part reflects distinct characteristics and variations specific to each task, allowing the model to address the unique aspects of different driving behaviors. Accordingly, the task-shared consequent part is characterized by low-rank property, which mines global structural information within the fuzzy space;whereas the task-specific consequent part exhibits sparsity, which removes non-discriminative and irrelevant information. This sparsity ensures that the model focuses on the most critical features for each specific task. Furthermore, a discriminative diversity term is introduced to enhance the diversity between tasks, which explores the consistent information of task-shared consequents while reducing the overlap of task-specific consequents. Experimental results indicate that the MD-TS-FM model can be effectively applied to driving behavior safety assessment. © 1975-2011 IEEE.

关键词： driving behavior safety assessment edge computing fuzzy model multitask learning

Decentralized and Lightweight Cross-Chain Transaction Scheme Based on Proxy Re-signature

学校读者我要写书评

暂无评论

Decentralized and Lightweight Cross-Chain Transaction Scheme...

IEEE International Conference on Trust, Security and Privacy in computing and Communications (TrustCom)

作者： Huiying Zou Jia Duan Xi Liu Wei Ren Tao Li Xianghan Zheng Kim-Kwang Raymond Choo School of Computer Science China University of Geosciences Wuhan China The Third Surveying and Mapping Institute of Hunan Province Hunan Engineering Research Center of Geographic Information Security and Application Hunan China Key Laboratory of Data Protection and Intelligent Management Sichuan University Ministry of Education China State Key Laboratory of Geo-Information Engineering and Key Laboratory of Surveying and Mapping Science and Geospatial Information Technology of MNR CASM Beijing China College of Computer and Big Data Fuzhou University School of Information and Intelligent Engineering Sanya College China Department of Information Systems and Cyber Security University of Texas at San Antonio San Antonio USA

ISBN: (数字)9798331506209

ISBN: (纸本)9798331506216

With the widespread application of digital assets and the rapid development of blockchain technology, achieving secure and efficient transactions between different blockchain networks has become an urgent challenge. Existing cross-chain methods impose limitations, e.g., hash lock technology exhibits low scalability, side-chain technology is overly complex, and notary schemes pose centralization risks. In order to address these issues, we propose a cross-chain transaction solution based on proxy re-signature technology. To tackle the centralization concerns, we employ proxy re-signature technology to decentralize the authority of notaries among transaction participants, minimizing the potential for centralization at a low cost. We further present an extended scheme that can guarantee more requirements such as higher transaction amount and shorter transaction time. Furthermore, we analyze and compare the signature technologies used in the proposed solution and provide a systematic proof of our approach’s security.

关键词： Privacy Systematics Costs Scalability Blockchains Security