检索结果-内蒙古大学图书馆

Ensemble Clustering via Co-association Matrix Self-enhancement

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jia, Yuheng Tao, Sirui Wang, Ran Wang, Yongheng The School of Computer Science and Engineering Southeast University Nanjing210096 China The Research Center for Big Data Intelligence Zhejiang Lab Hangzhou311121 China The School of Automation Southeast University Nanjing210096 China The College of Mathematics and Statistics Shenzhen University Shenzhen518060 China

Ensemble clustering integrates a set of base clustering results to generate a stronger one. Existing methods usually rely on a co-association (CA) matrix that measures how many times two samples are grouped into the same cluster according to the base clusterings to achieve ensemble clustering. However, when the constructed CA matrix is of low quality, the performance will degrade. In this paper, we propose a simple yet effective CA matrix self-enhancement framework that can improve the CA matrix to achieve better clustering performance. Specifically, we first extract the high-confidence (HC) information from the base clusterings to form a sparse HC matrix. By propagating the highly-reliable information of the HC matrix to the CA matrix and complementing the HC matrix according to the CA matrix simultaneously, the proposed method generates an enhanced CA matrix for better clustering. Technically, the proposed model is formulated as a symmetric constrained convex optimization problem, which is efficiently solved by an alternating iterative algorithm with convergence and global optimum theoretically guaranteed. Extensive experimental comparisons with twelve state-of-the-art methods on ten benchmark datasets substantiate the effectiveness, flexibility, and efficiency of the proposed model in ensemble clustering. The codes and datasets can be downloaded at https://***/Siritao/EC-CMS. Copyright © 2022, The Authors. All rights reserved.

关键词： Iterative methods

Towards Effective Clustered Federated Learning: A Peer-to-peer Framework with Adaptive Neighbor Matching

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Li, Zexi Lu, Jiaxun Luo, Shuang Zhu, Didi Shao, Yunfeng Li, Yinchuan Zhang, Zhimeng Wang, Yongheng Wu, Chao The College of Computer Science and Technology Zhejiang University Hangzhou China Huawei Noah's Ark Lab Beijing China The School of Public Affairs Zhejiang University Hangzhou China The School of Software Technology Zhejiang University Hangzhou China The Big Data Intelligence Research Center Zhejiang Lab Hangzhou China

In federated learning (FL), clients may have diverse objectives, and merging all clients' knowledge into one global model will cause negative transfer to local performance. Thus, clustered FL is proposed to group similar clients into clusters and maintain several global models. In the literature, centralized clustered FL algorithms require the assumption of the number of clusters and hence are not effective enough to explore the latent relationships among clients. In this paper, without assuming the number of clusters, we propose a peer-to-peer (P2P) FL algorithm named PANM. In PANM, clients communicate with peers to adaptively form an effective clustered topology. Specifically, we present two novel metrics for measuring client similarity and a two-stage neighbor matching algorithm based Monte Carlo method and Expectation Maximization under the Gaussian Mixture Model assumption. We have conducted theoretical analyses of PANM on the probability of neighbor estimation and the error gap to the clustered optimum. We have also implemented extensive experiments under both synthetic and real-world clustered heterogeneity. Theoretical analysis and empirical experiments show that the proposed algorithm is superior to the P2P FL counterparts, and it achieves better performance than the centralized cluster FL method. PANM is effective even under extremely low communication budgets. © 2022, CC BY.

关键词： Monte Carlo methods

BED: A Block-Level Deduplication-Based Container Deployment Framework 15th

学校读者我要写书评

暂无评论

BED: A Block-Level Deduplication-Based Container Deployment ...

15th International Conference on Green, Pervasive, and Cloud Computing, GPC 2020

作者： Zhang, Shiqiang Wu, Song Fan, Hao Zou, Deqing Jin, Hai 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 Scinece and Technology Wuhan430074 China

ISBN: (纸本)9783030642426

Container technology has gained great popularity in cloud environment since containers provide near-native performance and are lighter and less expensive than traditional virtual machines. However, starting up a non-local container, whose image is unavailable locally, is time-consuming. The reason is that pulling an image from a remote registry requires a long time. In this paper, we experimentally find that a lot of redundant data exists among image layers when we pull images from the registry. This redundant data causes additional pull time and makes the startup of a non-local container slower. To minimize the amount of pulled data while providing intact images, we propose a container deployment framework, BED, based on block-level deduplication. To be specific, BED stores an image layer as numerous data blocks and a fingerprint list which is generated based on these data blocks. When BED needs to pull an image, it pulls the fingerprint lists of the image, deduplicates these fingerprint lists, and pulls the data blocks non-existing locally from the registry. Based on the local and pulled blocks, BED reconstructs the image layers for a container. Experiments show that compared with original Docker, BED reduces the time of pulling images by 35% on average and saves about 48% data transmission in the network. © 2020, Springer Nature Switzerland AG.

关键词： Containers

Training Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xiao, Mingqing Meng, Qingyan Zhang, Zongpeng Wang, Yisen Lin, Zhouchen School of AI Peking University China The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data China Center for Data Science Academy for Advanced Interdisciplinary Studies Peking University China Pazhou Lab. Guangzhou510330 China

Spiking neural networks (SNNs) are brain-inspired models that enable energy-efficient implementation on neuromorphic hardware. However, the supervised training of SNNs remains a hard problem due to the discontinuity of the spiking neuron model. Most existing methods imitate the backpropagation framework and feedforward architectures for artificial neural networks, and use surrogate derivatives or compute gradients with respect to the spiking time to deal with the problem. These approaches either accumulate approximation errors or only propagate information limitedly through existing spikes, and usually require information propagation along time steps with large memory costs and biological implausibility. In this work, we consider feedback spiking neural networks, which are more brain-like, and propose a novel training method that does not rely on the exact reverse of the forward computation. First, we show that the average firing rates of SNNs with feedback connections would gradually evolve to an equilibrium state along time, which follows a fixed-point equation. Then by viewing the forward computation of feedback SNNs as a black-box solver for this equation, and leveraging the implicit differentiation on the equation, we can compute the gradient for parameters without considering the exact forward procedure. In this way, the forward and backward procedures are decoupled and therefore the problem of non-differentiable spiking functions is avoided. We also briefly discuss the biological plausibility of implicit differentiation, which only requires computing another equilibrium. Extensive experiments on MNIST, Fashion-MNIST, N-MNIST, CIFAR-10, and CIFAR-100 demonstrate the superior performance of our method for feedback models with fewer neurons and parameters in a small number of time steps. Our code is available at https://***/pkuxmq/IDE-FSNN. Copyright © 2021, The Authors. All rights reserved.

关键词： Feedback

Efficient unified information extraction model based on large language models

学校读者我要写书评

暂无评论

Applied Soft Computing 2025年 180卷

作者： Xieyun Zhang Shimin Cai Xiaorong Shen Han Yang Wenhao Hu Yanru Zhang Big Data Research Center University of Electronic Science and Technology of China Chengdu 611731 China i-Large Model innovation Lab of Ideological and Political Science University of Electronic Science and Technology of China Chengdu 611731 China

Large Language Models (LLMs) have shown underperformance in information extraction (IE) tasks compared to smaller models. This underperformance is largely attributed to the mismatch between IE’s structured output and LLMs’ natural language output and the absence of IE tasks in the pre-training corpus. Furthermore, prior research aimed to adapt LLMs to IE tasks through instructional design without updating model parameters, or by fine-tuning them with substantial computational resources, at the expense of their original performance in other tasks. Inspired by the Parameter Efficient Fine-Tuning (PEFT) technique, we designed an efficient unified information framework for LLMs (LLM-UIE), which performs domain adaptation fine-tuning with low resource requirements. Importantly, LLM-UIE introduced an additional answer selection task to improve LLMs’ ability to generate desired answers, efficiently addressing the inconsistency between LLMs’ fuzzy outputs and standard answers. Experiments on extensive information extraction datasets show that LLM-UIE not only matches but even surpasses the F1 scores of state-of-the-art models while demonstrating significant advantages in training efficiency, substantially reducing training time. Moreover, compared to previous LLM-based studies, LLM-UIE significantly lowers computational resource requirements.

关键词： Online searching

K-Space-Aware Cross-Modality Score for Quality Assessment of Synthesized Neuroimages

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xie, Guoyang Wang, Jinbao Huang, Yawen Lyu, Jiayi Zheng, Feng Zheng, Yefeng Jin, Yaochu Southern University of Science and Technology Department of Computer Science Shenzhen518055 China CATL Department of Intelligent Manufacturing Ningde352000 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Tencent Youtu Lab Jarvis Research Center Shenzhen510310 China University of Chinese Academy of Sciences the School of Engineering Science Beijing100049 China Westlake University the School of Engineering Hangzhou310030 China

The problem of how to assess cross-modality medical image synthesis has been largely unexplored. The most used measures like PSNR and SSIM focus on analyzing the structural features but neglect the crucial lesion location and fundamental k-space speciality of medical images. To overcome this problem, we propose a new metric K-CROSS to spur progress on this challenging problem. Specifically, K-CROSS uses a pre-trained multi-modality segmentation network to predict the lesion location, together with a tumor encoder for representing features, such as texture details and brightness intensities. To further reflect the frequency-specific information from the magnetic resonance imaging principles, both k-space features and vision features are obtained and employed in our comprehensive encoders with a frequency reconstruction penalty. The structure-shared encoders are designed and constrained with a similarity loss to capture the intrinsic common structural information for both modalities. As a consequence, the features learned from lesion regions, k-space, and anatomical structures are all captured, which serve as our quality evaluators. We evaluate the performance by constructing a large-scale cross-modality neuroimaging perceptual similarity (NIRPS) dataset with 6,000 radiologist judgments. Extensive experiments demonstrate that the proposed method outperforms other metrics, especially in comparison with the radiologists on NIRPS. To forster reproducibility and accessibility, the source codeis uploaded to the website: https://***/M-3lab/K-CROSS © 2023, CC BY.

关键词： Magnetic resonance imaging

Be Water, My Antennas: Riding on Radio Wave Fluctuation in Nature for Spatial Multiplexing using Programmable Meta-Fluid Antenna

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Baiyang Tong, Kin-Fai Wong, Kai-Kit Chae, Chan-Byoung Wong, Hang College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China State Key Laboratory of Terahertz and Millimeter Waves Department of Electrical Engineering City University of Hong Kong Hong Kong School of Science and Technology Hong Kong Metropolitan University Hong Kong Department of Electronic and Electrical Engineering University College London LondonWC1E7JE United Kingdom Yonsei Frontier Lab Yonsei University Korea Republic of

Interference and scattering, often deemed undesirable, are inevitable in wireless communications, especially when the current mobile networks and upcoming sixth generation (6G) have turned into ultra-dense networks. Current approaches relying on multiple-input multiple-output (MIMO) combined with artificial-intelligence-aided (AI) signal processing have drawbacks of being power-hungry and requiring wide bandwidth that raise scalability concerns. In this article, we take a radical approach and utilize the channel fading phenomenon to our advantage. Specifically, we propose a novel meta-fluid antenna architecture, referred to as the ‘fluid’ antenna system (FAS), that can freely surf on radio wave fluctuations, like ‘fluid’ figuratively speaking, with fine resolution in space to opportunistically avoid interference, eliminating the need for expensive signal processing. Our experimental results demonstrate that under rich scattering conditions, the proposed meta-fluidic architecture is able to exploit the natural ups and downs of radio waves in space for spatial multiplexing. These breakthrough results show that scattering can be desirable not harmful and interference can be dodged not suppressed, fundamentally changing our perception of fading and our understanding on how interference should be managed in wireless communications networks. © 2025, CC0.

关键词： Fading (radio)

Spatio-Temporal Stratified Associations between Urban Human Activities and Crime Patterns: A Case Study in San Francisco Around the Covid-19 Stay-at-Home Mandate

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Chen, Tongxin Bowers, Kate Zhu, Di Gao, Xiaowei Cheng, Tao Space Time Lab for Big Data Analytics Department of Civil Environmental and Geomatic Engineering University College London LondonWC1E 6BT United Kingdom Department of Security and Crime Science University College London LondonWC1H 9EZ United Kingdom Geospatial Data Intelligence Lab Department of Geography Environment and Society University of Minnesota Twin Cities Minneapolis55455 United States

Crime changes have been reported as a result of human routine activity shifting due to containment policies, such as stay-at-home (SAH) mandates during the COVID-19 pandemic. However, the way in which the manifestation of crime in both space and time is affected by dynamic human activities in urban areas has not been explored in depth in empirical studies hitherto. Here, we aim to quantitatively measure the spatio-temporal associations between crime patterns and human activities in the context of an unstable period of the ever-changing socio-demographic backcloth. We propose an analytical framework to detect the dynamic stratified associations between the spatial distributions of human activities and crimes. The results of a case study in San Francisco, United States reveal that the spatial patterns of most crime types are statistically significantly associated with that of human activities zones. Property crime exhibits higher stratified association than violent crime across all temporal scales. Further, the strongest association is obtained with the eight-week time span centered around the SAH order. These findings not only enhance our understanding of the relationships between urban crime and human activities, but also offer insights that tailored crime intervention strategies need to consider human activity variables. © 2022, The Authors. All rights reserved.

关键词： Crime

Foundation models in bioinformatics

学校读者我要写书评

暂无评论

National science Review 2025年第4期 400-418页

作者： Fei Guo Renchu Guan Yaohang Li Qi Liu Xiaowo Wang Can Yang Jianxin Wang Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Xiangjiang Laboratory Key Laboratory for Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Department of Computer Science Old Dominion University School of Life Sciences and Technology Tongji University Department of Automation Tsinghua University Department of Mathematics State Key Laboratory of Molecular Neuroscience and Big Data Bio-Intelligence Lab The Hong Kong University of Science and Technology

With the adoption of foundation models(FMs),artificial intelligence(AI) has become increasingly significant in bioinformatics and has successfully addressed many historical challenges,such as pre-training frameworks,model evaluation and *** demonstrate notable proficiency in managing large-scale,unlabeled datasets,because experimental procedures are costly and labor *** various downstream tasks,FMs have consistently achieved noteworthy results,demonstrating high levels of accuracy in representing biological entities.A new era in computational biology has been ushered in by the application of FMs,focusing on both general and specific biological *** this review,we introduce recent advancements in bioinformatics FMs employed in a variety of downstream tasks,including genomics,transcriptomics,proteomics,drug discovery and single-cell *** aim is to assist scientists in selecting appropriate FMs in bioinformatics,according to four model types:language FMs,vision FMs,graph FMs and multimodal *** addition to understanding molecular landscapes,AI technology can establish the theoretical and practical foundation for continued innovation in molecular biology.

关键词：