检索结果-南通市图书馆

Federatedmutual learning:a collaborative machine learning method for heterogeneous data,models,and objectives

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2023年第10期24卷 1390-1402页

作者： Tao SHEN Jie ZHANG Xinkang JIA Fengda ZHANG Zheqi LV Kun KUANG Chao WU Fei WU College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China School of Software Technology Zhejiang UniversityHangzhou 310027China School of Public Affairs Zhejiang UniversityHangzhou 310027China

Federated learning(FL)is a novel technique in deep learning that enables clients to collaboratively train a shared model while retaining their decentralized data.However,researchers working on FL face several unique challenges,especially in the context of heterogeneity.Heterogeneity in data distributions,computational capabilities,and scenarios among clients necessitates the development of customized models and objectives in FL.Unfortunately,existing works such as FedAvg may not effectively accommodate the specific needs of each client.To address the challenges arising from heterogeneity in FL,we provide an overview of the heterogeneities in data,model,and objective(DMO).Furthermore,we propose a novel framework called federated mutual learning(FML),which enables each client to train a personalized model that accounts for the data heterogeneity(DH).A“meme model”serves as an intermediary between the personalized and global models to address model heterogeneity(MH).We introduce a knowledge distillation technique called deep mutual learning(DML)to transfer knowledge between these two models on local data.To overcome objective heterogeneity(OH),we design a shared global model that includes only certain parts,and the personalized model is task-specific and enhanced through mutual learning with the meme model.We evaluate the performance of FML in addressing DMO heterogeneities through experiments and compare it with other commonly used FL methods in similar scenarios.The results demonstrate that FML outperforms other methods and effectively addresses the DMO challenges encountered in the FL setting.

关键词： Federated learning Knowledge distillation Privacy preserving Heterogeneous environment

在线全文

学校读者我要写书评

暂无评论

群体智能系统的结构分析

Engineering 2023年第6期25卷 17-20页

作者：潘云鹤 Artificial Intelligence Institute Zhejiang UniversityHangzhou 310027China Zhijiang Lab Hangzhou 310027China

1. The connotation and characteristics of crowd intelligence The reason that human beings have evolved to such an advanced level today lies not only in the increase in individual knowledge but also in the structural progress of crowds [1]. Given the importance of the latter, since the late 20th century, researchers have begun to explore management and calculation methods related to crowd intelligence [2], such as the multiagent system,distributed collaboration, and open-source platform.

关键词：群体智能 individual latter

UI layers merger: merging UI layers via visual learning and boundary prior

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2023年第3期24卷 373-387页

作者： Yunnong CHEN Yankun ZHEN Chuning SHI Jiazhi LI Liuqing CHEN Zejian LI Lingyun SUN Tingting ZHOU Yanfang CHANG School of Software Technology Zhejiang UniversityHangzhou 310027China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies Hangzhou 310027China Alibaba Group Hangzhou 311121China Zhejiang-Singapore Innovation and AI Joint Research Lab Hangzhou 310027China

With the fast-growing graphical user interface(GUI)development workload in the Internet industry,some work attempted to generate maintainable front-end code from GUI screenshots.It can be more suitable for using user interface(UI)design drafts that contain UI metadata.However,fragmented layers inevitably appear in the UI design drafts,which greatly reduces the quality of the generated code.None of the existing automated GUI techniques detects and merges the fragmented layers to improve the accessibility of generated code.In this paper,we propose UI layers merger(UILM),a vision-based method that can automatically detect and merge fragmented layers into UI components.Our UILM contains the merging area detector(MAD)and a layer merging algorithm.The MAD incorporates the boundary prior knowledge to accurately detect the boundaries of UI components.Then,the layer merging algorithm can search for the associated layers within the components’boundaries and merge them into a whole.We present a dynamic data augmentation approach to boost the performance of MAD.We also construct a large-scale UI dataset for training the MAD and testing the performance of UILM.Experimental results show that the proposed method outperforms the best baseline regarding merging area detection and achieves decent layer merging accuracy.A user study on a real application also confirms the effectiveness of our UILM.

关键词： User interface(UI)to code UI design lint UI layer merging Object detection

Soft-HGRNs:soft hierarchical graph recurrent networks for multi-agent partially observable environments

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2023年第1期24卷 117-130页

作者： Yixiang REN Zhenhui YE Yining CHEN Xiaohong JIANG Guanghua SONG School of Aeronautics and Astronautics Zhejiang UniversityHangzhou 310027China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China

The recent progress in multi-agent deep reinforcement learning(MADRL)makes it more practical in real-world tasks,but its relatively poor scalability and the partially observable constraint raise more challenges for its performance and deployment.Based on our intuitive observation that human society could be regarded as a large-scale partially observable environment,where everyone has the functions of communicating with neighbors and remembering his/her own experience,we propose a novel network structure called the hierarchical graph recurrent network(HGRN)for multi-agent cooperation under partial observability.Specifically,we construct the multiagent system as a graph,use a novel graph convolution structure to achieve communication between heterogeneous neighboring agents,and adopt a recurrent unit to enable agents to record historical information.To encourage exploration and improve robustness,we design a maximum-entropy learning method that can learn stochastic policies of a configurable target action entropy.Based on the above technologies,we propose a value-based MADRL algorithm called Soft-HGRN and its actor-critic variant called SAC-HGRN.Experimental results based on three homogeneous tasks and one heterogeneous environment not only show that our approach achieves clear improvements compared with four MADRL baselines,but also demonstrate the interpretability,scalability,and transferability of the proposed model.

关键词： Deep reinforcement learning Graph-based communication Maximum-entropy learning Partial observability Heterogeneous settings

Visual knowledge guided intelligent generation of Chinese seal carving

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2022年第10期23卷 1479-1493页

作者： Kejun ZHANG Rui ZHANG Yehang YIN Yifei LI Wenqi WU Lingyun SUN Fei WU Huanghuang DENG Yunhe PAN College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China Alibaba-Zhejiang University Joint Institute of Frontier Technologies Hangzhou 310027China School of Software Technology Zhejiang UniversityHangzhou 310027China

We digitally reproduce the process of resource collaboration,design creation,and visual presentation of Chinese seal-carving art.We develop an intelligent seal-carving art-generation system(Zhejiang University Intelligent Seal-Carving System,http://***/seal/;the website of the seal-carving search and layout system is http://***/seal/search_app/)to deal with the difficulty in using a visual knowledge guided computational art approach.The knowledge base in this study is the Qiushi Seal-Carving Database,which consists of open datasets of images of seal characters and seal stamps.We propose a seal character generation method based on visual knowledge,guided by the database and expertise.Furthermore,to create the layout of the seal,we propose a deformation algorithm to adjust the seal characters and calculate layout parameters from the database and knowledge to achieve an intelligent structure.Experimental results show that this method and system can effectively deal with the difficulties in the generation of seal carving.Our work provides theoretical and applied references for the rebirth and innovation of seal-carving art.

关键词： Seal-carving Intelligent generation Deep learning Parametric modeling Computational art

Effect of cognitive training on brain dynamics

在线全文

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第2期33卷 529-536页

作者：吕贵阳徐天勇陈飞燕朱萍王淼何国光 School of Physics Zhejiang UniversityHangzhou 310027China

The human brain is highly plastic.Cognitive training is usually used to modify functional connectivity of brain networks.Moreover,the structures of brain networks may determine its dynamic behavior which is related to human cognitive abilities.To study the effect of functional connectivity on the brain dynamics,the dynamic model based on functional connections of the brain and the Hindmarsh–Rose model is utilized in this work.The resting-state fMRI data from the experimental group undergoing abacus-based mental calculation(AMC)training and from the control group are used to construct the functional brain networks.The dynamic behavior of brain at the resting and task states for the AMC group and the control group are simulated with the above-mentioned dynamic model.In the resting state,there are the differences of brain activation between the AMC group and the control group,and more brain regions are inspired in the AMC group.A stimulus with sinusoidal signals to brain networks is introduced to simulate the brain dynamics in the task states.The dynamic characteristics are extracted by the excitation rates,the response intensities and the state distributions.The change in the functional connectivity of brain networks with the AMC training would in turn improve the brain response to external stimulus,and make the brain more efficient in processing tasks.

关键词： brian dynamics functional brain networks cognitive training abacus-based mental calculation

Smart grid dispatch powered by deep learning:a survey

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2022年第5期23卷 763-776页

作者： Gang HUANG Fei WU Chuangxin GUO Zhejiang Lab Hangzhou 311121China College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China College of Electrical Engineering Zhejiang UniversityHangzhou 310027China

Power dispatch is a core problem for smart grid operations.It aims to provide optimal operating points within a transmission network while power demands are changing over space and time.This function needs to be run every few minutes throughout the day;thus,a fast,accurate solution is of vital importance.However,due to the complexity of the problem,reliable and computationally efficient solutions are still under development.This issue will become more urgent and complicated as the integration of intermittent renewable energies increases and the severity of uncertain disasters gets worse.With the recent success of artificial intelligence in various industries,deep learning becomes a promising direction for power engineering as well,and the research community begins to rethink the problem of power dispatch.This paper reviews the recent progress in smart grid dispatch from a deep learning perspective.Through this paper,we hope to advance not only the development of smart grids but also the ecosystem of artificial intelligence.

关键词： Artificial intelligence Deep learning Power dispatch Smart grid

Pyramid-VAE-GAN:Transferring hierarchical latent variables for image inpainting

在线全文

学校读者我要写书评

暂无评论

Computational Visual Media 2023年第4期9卷 827-841页

作者： Huiyuan Tian Li Zhang Shijian Li Min Yao Gang Pan College of Computer Science and Technology Zhejiang UniversityHangzhou 310027China Advanced Technology Research Institute Zhejiang UniversityHangzhou 310027China

Significant progress has been made in image inpainting methods in recent years.However,they are incapable of producing inpainting results with reasonable structures,rich detail,and sharpness at the same time.In this paper,we propose the Pyramid-VAE-GAN network for image inpainting to address this limitation.Our network is built on a variational autoencoder(VAE)backbone that encodes high-level latent variables to represent complicated high-dimensional prior distributions of images.The prior assists in reconstructing reasonable structures when inpainting.We also adopt a pyramid structure in our model to maintain rich detail in low-level latent variables.To avoid the usual incompatibility of requiring both reasonable structures and rich detail,we propose a novel cross-layer latent variable transfer module.This transfers information about long-range structures contained in high-level latent variables to low-level latent variables representing more detailed information.We further use adversarial training to select the most reasonable results and to improve the sharpness of the images.Extensive experimental results on multiple datasets demonstrate the superiority of our method.Our code is available at https://***/thy960112/Pyramid-VAE-GAN.

关键词： image inpainting variational autoencoder(VAE) latent variable transfer(LTN) pyramid structure generative model

A CLASS OF INVERSE QUOTIENT CURVATURE FLOW IN THE ADS-SCHWARZSCHILD MANIFOLD

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Scientia 2023年第6期43卷 2553-2572页

作者：纪正超 Zhejiang Institute of Modern Physics Zhejiang UniversityHangzhou 310027China Center of Mathematical Sciences Zhejiang UniversityHangzhou 310027China

In this paper,we study the asymptotic behavior of a class of inverse quotient curvature flow in the anti-de Sitter-Schwarzschild manifold.We prove that under suitable convex conditions for the initial hypersurface,one can get the long-time existence for the inverse curvature flow.Moreover,we also get that the principal curvatures of the evolving hypersurface converge to 1 when t→+∞.

关键词： star-shaped quotient curvature support function