检索结果-内蒙古大学图书馆

Computationally Efficient Approximations for Matrix-based Rényi's Entropy

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gong, Tieliang Dong, Yuxin Yu, Shujian Dong, Bo The School of Computer Science and Technology Xi'an Jiaotong University Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an710049 China The Machine Learning Group UiT - The Arctic University of Norway Department of Computer Science Vrije University Amsterdam Amsterdam Netherlands

The recently developed matrix-based Rényi's αorder entropy enables measurement of information in data simply using the eigenspectrum of symmetric positive semi-definite (PSD) matrices in reproducing kernel Hilbert space, without estimation of the underlying data distribution. This intriguing property makes this new information measurement widely adopted in multiple statistical inference and learning tasks. However, the computation of such quantity involves the trace operator on a PSD matrix G to power α (i.e., tr(Gα)), with a normal complexity of nearly O(n3), which severely hampers its practical usage when the number of samples (i.e., n) is large. In this work, we present computationally efficient approximations to this new entropy functional that can reduce its complexity to even significantly less than O(n2). To this end, we leverage the recent progress on Randomized Numerical Linear Algebra, developing Taylor, Chebyshev and Lanczos approximations to tr(Gα) for arbitrary values of α by converting it into a matrix-vector multiplication problem. We also establish the connection between the matrix-based Rényi's entropy and PSD matrix approximation, which enables exploiting both clustering and block low-rank structure of G to further reduce the computational cost. We theoretically provide approximation accuracy guarantees and illustrate the properties for different approximations. Large-scale experimental evaluations on both synthetic and real-world data corroborate our theoretical findings, showing promising speedup with negligible loss in accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： Matrix algebra

Human-in-The-Loop Optimization for Vehicle Body Lightweight Design

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Hao, Jia Deng, Ruofan Jia, Liangyue Li, Zuoxuan Industrial and Systems Engineering Laboratory Beijing Institute of Technology Beijing100081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314019 China Key Laboratory of Industry Knowledge & Data Fusion Technology and Application Ministry of Industry and Information Technology Beijing Institute of Technology Beijing100081 China

Automatic optimization algorithms play an important role in vehicle body lightweight design;however, the existing methods are still inefficient and result in excessive iterations that escalate both time and costs. Current interactive optimization strategies partially mitigate this issue but fall short in offering a broad spectrum of manipulation points and auxiliary information model, essential for optimizing design efficiency and accuracy. As such, we introduce a novel approach, "Human-in-the-Loop based method for Vehicle Body Lightweight Design" (HIL-VBLD). This method seamlessly integrates human decision-making with optimization algorithms to reduce unproductive iterations. HIL-VBLD comprises two key components: (1) a novel interaction mode offering multiple manipulation points including constraint modification, algorithm switching, and selection of solutions of interest (SOI);(2) A comprehensive auxiliary information model aids in decision-making for designers. Our analysis underscores HIL-VBLD's efficacy, evidenced by a 54.5% reduction in iteration cycles for genetic algorithm using SOI selection. Algorithm switching led to a 4.5% mass reduction, circumventing local optimum pitfalls associated with gradient algorithms. Additionally, the auxiliary information model contributed to a further 1.25% mass reduction, enhancing optimization robustness. Compared to conventional automatic algorithm switching strategies, HIL-VBLD maintains equivalent accuracy with 23.9% fewer iterations. © 2024, The Authors. All rights reserved.

关键词： Genetic algorithms

Multi-frame joint enhancement for early interlaced videos

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhao, Yang Ma, Yanbo Chen, Yuan Jia, Wei Wang, Ronggang Liu, Xiaoping The Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei230009 China The School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China The School of Electronic and Computer Engineering Peking University Shenzhen Graduate School 2199 Lishui Road Shenzhen518055 China Peng Cheng Laboratory Shenzhen518000 China

Early interlaced videos usually contain multiple and interlacing and complex compression artifacts, which significantly reduce the visual quality. Although the high-definition reconstruction technology for early videos has made great progress in recent years, related research on deinterlacing is still lacking. Traditional methods mainly focus on simple interlacing mechanism, and cannot deal with the complex artifacts in real-world early videos. Recent interlaced video reconstruction deep deinterlacing models only focus on single frame, while neglecting important temporal information. Therefore, this paper proposes a multiframe deinterlacing network joint enhancement network for early interlaced videos that consists of three modules, i.e., spatial vertical interpolation module, temporal alignment and fusion module, and final refinement module. The proposed method can effectively remove the complex artifacts in early videos by using temporal redundancy of multi-fields. Experimental results demonstrate that the proposed method can recover high quality results for both synthetic dataset and real-world early interlaced videos. Copyright © 2021, The Authors. All rights reserved.

关键词： Image reconstruction

ER: Equivariance Regularizer for knowledge Graph Completion

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cao, Zongsheng Xu, Qianqian Yang, Zhiyong Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

Tensor factorization and distanced based models play important roles in knowledge graph completion (KGC). However, the relational matrices in KGC methods often induce a high model complexity, bearing a high risk of overfitting. As a remedy, researchers propose a variety of different regularizers such as the tensor nuclear norm regularizer. Our motivation is based on the observation that the previous work only focuses on the "size" of the parametric space, while leaving the implicit semantic information widely untouched. To address this issue, we propose a new regularizer, namely, Equivariance Regularizer (ER), which can suppress overfitting by leveraging the implicit semantic information. Specifically, ER can enhance the generalization ability of the model by employing the semantic equivariance between the head and tail entities. Moreover, it is a generic solution for both distance based models and tensor factorization based models. The experimental results indicate a clear and substantial improvement over the state-of-the-art relation prediction methods. © 2022, CC BY.

关键词： knowledge graph

Geometry Interaction knowledge Graph Embeddings

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cao, Zongsheng Xu, Qianqian Yang, Zhiyong Cao, Xiaochun Huang, Qingming State Key Laboratory of Information Security Institute of Information Engineering CAS Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China Peng Cheng Laboratory Shenzhen China

knowledge graph (KG) embeddings have shown great power in learning representations of entities and relations for link prediction tasks. Previous work usually embeds KGs into a single geometric space such as Euclidean space (zero curved), hyperbolic space (negatively curved) or hyperspherical space (positively curved) to maintain their specific geometric structures (e.g., chain, hierarchy and ring structures). However, the topological structure of KGs appears to be complicated, since it may contain multiple types of geometric structures simultaneously. Therefore, embedding KGs in a single space, no matter the Euclidean space, hyperbolic space or hyperspheric space, cannot capture the complex structures of KGs accurately. To overcome this challenge, we propose Geometry Interaction knowledge graph Embeddings (GIE), which learns spatial structures interactively between the Euclidean, hyperbolic and hyperspherical spaces. Theoretically, our proposed GIE can capture a richer set of relational information, model key inference patterns, and enable expressive semantic matching across entities. Experimental results on three well-established knowledge graph completion benchmarks show that our GIE achieves the state-of-the-art performance with fewer parameters. © 2022, CC BY.

关键词： knowledge graph

Few-shot Open Relation Extraction with Gaussian Prototype and Adaptive Margin

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Tianlin Zhang, Lingling Wang, Jiaxin Lei, Yunkuo Li, Yifei Wang, Haofen Liu, Jun School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi’an710049 China School of Computer Science and Technology Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi’an710049 China College of Design and Innovation Tongji University Shanghai200092 China

Few-shot relation extraction with none-of-the-above (FsRE with NOTA) aims at predicting labels in few-shot scenarios with unknown classes. FsRE with NOTA is more challenging than the conventional few-shot relation extraction task, since the boundaries of unknown classes are complex and difficult to learn. Meta-learning based methods, especially prototype-based methods, are the mainstream solutions to this task. They obtain the classification boundary by learning the sample distribution of each class. However, their performance is limited because few-shot overfitting and NOTA boundary confusion lead to misclassification between known and unknown classes. To this end, we propose a novel framework based on Gaussian prototype and adaptive margin named GPAM for FsRE with NOTA, which includes three modules, semi-factual representation, GMM-prototype metric learning and decision boundary learning. The first two modules obtain better representations to solve the few-shot problem through debiased information enhancement and Gaussian space distance measurement. The third module learns more accurate classification boundaries and prototypes through adaptive margin and negative sampling. In the training procedure of GPAM, we use contrastive learning loss to comprehensively consider the effects of range and margin on the classification of known and unknown classes to ensure the model's stability and robustness. Sufficient experiments and ablations on the FewRel dataset show that GPAM surpasses previous prototype methods and achieves state-of-the-art performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

Digital Mahjong System: Towards Precise Cognitive Assessment with IoT Technologies 1

学校读者我要写书评

暂无评论

24th International Conference on Human-Computer Interaction, HCII 2022

作者： An, Ning Hu, Enze Guo, Yanrui Yang, Jiaoyun Au, Rhoda Ding, Huitong School of Computer Science and Information Engineering Hefei University of Technology Hefei China Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China National Smart Eldercare International S&T Cooperation Base Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China Shenzhen Corecloud Innovation Technology Co. Ltd. Shenzhen China Key Laboratory of Knowledge Engineering with Big Data of Ministry of Education Hefei University of Technology Hefei China Department of Anatomy and Neurobiology Neurology and Framingham Heart Study Boston University School of Medicine Boston United States Department of Epidemiology Boston University School of Public Health Boston United States

ISBN: (数字)9783031179020

ISBN: (纸本)9783031179013

To the best of our knowledge, this paper is the first to apply IoT technologies to transform the popular Mahjong game into a Digital Mahjong System (DMS) for digitally performing cognitive assessments. People have started exploring digital cognitive assessment tools for better objectivity and simplification. However, most of these tools are not friendly for older adults. This paper aims to address this issue by integrating IoT technologies with Mahjong to make cognitive assessment simpler and more engaging for older adults. DMS has the following features: 1) integrating motion tracking devices into Mahjong tiles and transferring them into Digital Mahjong Tiles (DMTs), which can precisely capture their moving trajectory during the assessment, 2) using a Near Field Communication reader to configure DMT’s primary data, 3) supporting Over-The-Air Device Firmware Update that can be done remotely via Bluetooth, and 4) developing a charging base that can charge 16 DMTs simultaneously using Qi wireless charging standard. With further testing, the DMS has the potential to become a digital platform to implement and test various cognitive assessment tools integrating Mahjong elements. © 2022, Springer Nature Switzerland AG.

关键词： Internet of things

Pathological brain detection based on online sequential extreme learning machine

学校读者我要写书评

暂无评论

Pathological brain detection based on online sequential extr...

IEEE International Conference on Progress in Informatics and Computing (PIC)

作者： Siyuan Lu Hainan Wang Xueyan Wu Shuihua Wang School of Computer Science and Technology Nanjing Normal University Nanjing Jiangsu China State Key Lab of CAD & CG Zhejiang University Hangzhou Zhejiang China Key laboratory of symbolic computation and knowledge engineering of ministry of education Jilin University Changchun Jilin China Key Laboratory of Statistical information technology and data mining State Statistics Bureau Chengdu Sichuan China Department of Electrical Engineering CUNY New York NY USA

ISBN: (纸本)9781509034857

Magnetic resonance imaging (MRI) is a kind of imaging modality, which offers clearer images of soft tissues than computed tomography (CT). It is especially suitable for brain disease detection. It is beneficial to detect diseases automatically and accurately. We proposed a pathological brain detection method based on brain MR images and online sequential extreme learning machine. First, seven wavelet entropies (WE) were extracted from each brain MR image to form the feature vector. Then, an online sequential extreme learning machine (OS-ELM) was trained to differentiate pathological brains from the healthy controls. The experiment results over 132 brain MRIs showed that the proposed approach achieved a sensitivity of 93.51%, a specificity of 92.22%, and an overall accuracy of 93.33%, which suggested that our method is effective.

关键词： Entropy Discrete wavelet transforms Feature extraction Pathology Training Magnetic resonance imaging Diseases

Stacked convolutional sparse auto-encoders for representation learning

学校读者我要写书评

暂无评论

ACM Transactions on knowledge Discovery from data 2021年第2期15卷 31-31页

作者： Zhu, Yi Li, Lei Wu, Xindong School of Information Engineering Yangzhou University China School of Computer Science and Information Engineering Hefei University of Technology China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei China Mininglamp Academy of Sciences Minininglamp Beijing 100084 China

Deep learning seeks to achieve excellent performance for representation learning in image datasets. However, supervised deep learning models such as convolutional neural networks require a large number of labeled image data, which is intractable in applications, while unsupervised deep learning models like stacked denoising auto-encoder cannot employ label information. Meanwhile, the redundancy of image data incurs performance degradation on representation learning for aforementioned models. To address these problems, we propose a semi-supervised deep learning framework called stacked convolutional sparse auto-encoder, which can learn robust and sparse representations from image data with fewer labeled data records. More specifically, the framework is constructed by stacking layers. In each layer, higher layer feature representations are generated by features of lower layers in a convolutional way with kernels learned by a sparse auto-encoder. Meanwhile, to solve the data redundance problem, the algorithm of Reconstruction Independent Component Analysis is designed to train on patches for sphering the input data. The label information is encoded using a Softmax Regression model for semi-supervised learning. With this framework, higher level representations are learned by layers mapping from image data. It can boost the performance of the base subsequent classifiers such as support vector machines. Extensive experiments demonstrate the superior classification performance of our framework compared to several state-of-the-art representation learning methods. © 2021 ACM.

关键词： Representation learning Sparse auto-encoder