检索结果-内蒙古大学图书馆

Optimal Linear Crossover for Mitigating Negative Transfer in Evolutionary Multitasking

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2024年

作者： Liu, Zhaobo Yuan, Jianhua Zhang, Haili Zeng, Tao Zhu, Zexuan Shenzhen University Institute for Advanced Study Shenzhen518060 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Shenzhen Polytechnic University School of Undergraduate Education Shenzhen518055 China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Shenzhen University Shenzhen City Key Laboratory of Embedded System Design Shenzhen518060 China Chongqing University Key Laboratory of Dependable Service Computing in Cyber Physical Society Ministry of Education of China Chongqing400044 China

Evolutionary multitasking algorithms use information exchange among individuals in a population to solve multiple optimization problems simultaneously. Negative transfer is a critical factor that affects the performance of evolutionary multitasking algorithms. In this study, we propose an innovative approach to mitigate negative transfer in evolutionary multitasking algorithms. The proposed approach is grounded in rigorous theoretical analysis, which provides valuable theoretical insights into the design of an optimal linear crossover operator for mitigating negative transfer. By identifying interpretable conditions, we establish a solid theoretical foundation to prevent negative transfer in diverse scenarios. Building upon these findings, we theoretically derive a closed-form expression for the optimal crossover operator and propose practical design methods based on approximations. Furthermore, we integrate the proposed optimal crossover operator into a fundamental evolutionary multitasking algorithm framework. The resultant algorithm is comparable or superior to other state-of-the-art methods. Empirical validation through comprehensive experiments confirms the effectiveness of our theoretical findings. © 1997-2012 IEEE.

关键词： Optimization algorithms

AOCC-FL: Federated Learning with Aligned Overlapping via Calibrated Compensation

学校读者我要写书评

暂无评论

AOCC-FL: Federated Learning with Aligned Overlapping via Cal...

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

作者： Haozhao Wang Wenchao Xu Yunfeng Fan Ruixuan Li Pan Zhou School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Department of Computing The Hong Kong Polytechnic University Hong Kong Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

Federated Learning enables collaboratively model training among a number of distributed devices with the coordination of a centralized server, where each device alternatively performs local gradient computation and communication to the server. FL suffers from significant performance degradation due to the excessive communication delay between the server and devices, especially when the network bandwidth of these devices is limited, which is common in edge environments. Existing methods overlap the gradient computation and communication to hide the communication latency to accelerate the FL training. However, the overlapping can also lead to an inevitable gap between the local model in each device and the global model in the server that seriously restricts the convergence rate of learning process. To address this problem, we propose a new overlapping method for FL, AOCC-FL, which aligns the local model with the global model via calibrated compensation such that the communication delay can be hidden without deteriorating the convergence performance. Theoretically, we prove that AOCC-FL admits the same convergence rate as the non-overlapping method. On both simulated and testbed experiments, we show that AOCC-FL achieves a comparable convergence rate relative to the non-overlapping method while outperforming the state-of-the-art overlapping methods.

关键词：

Variational Bayes for Federated Continual Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yao, Dezhong Li, Sanmu Dai, Yutong Xu, Zhiqiang Hu, Shengshan Zhao, Peilin Sun, Lichao The 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 Science and Technology Wuhan430074 China Lehigh University PA18015 United States Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates Tencent AI Lab. Shenzhen China

Federated continual learning (FCL) has received increasing attention due to its potential in handling real-world streaming data, characterized by evolving data distributions and varying client classes over time. The constraints of storage limitations and privacy concerns confine local models to exclusively access the present data within each learning cycle. Consequently, this restriction induces performance degradation in model training on previous data, termed "catastrophic forgetting". However, existing FCL approaches need to identify or know changes in data distribution, which is difficult in the real world. To release these limitations, this paper directs attention to a broader continuous framework. Within this framework, we introduce Federated Bayesian Neural Network (FedBNN), a versatile and efficacious framework employing a variational Bayesian neural network across all clients. Our method continually integrates knowledge from local and historical data distributions into a single model, adeptly learning from new data distributions while retaining performance on historical distributions. We rigorously evaluate FedBNN’s performance against prevalent methods in federated learning and continual learning using various metrics. Experimental analyses across diverse datasets demonstrate that FedBNN achieves state-of-the-art results in mitigating forgetting. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

WebCode2M: A Real-World dataset for Code Generation from Webpage Designs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gui, Yi Li, Zhen Wan, Yao Shi, Yemin Zhang, Hongyu Su, Yi Chen, Bohua Chen, Dongping Wu, Siyuan Zhou, Xing Jiang, Wenbin Jin, Hai Zhang, Xiangliang Huazhong University of Science and Technology Wuhan China Peking University Beijing China Chongqing University Chongqing China Hubei University of Automotive Technology Shiyan China Rabbitpre AI Shenzhen China University of Notre Dame Notre Dame United States 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

Automatically generating webpage code from webpage designs can significantly reduce the workload of front-end developers, and recent Multimodal Large Language Models (MLLMs) have shown promising potential in this area. However, our investigation reveals that most existing MLLMs are constrained by the absence of high-quality, large-scale, real-world datasets, resulting in inadequate performance in automated webpage code generation. To fill this gap, this paper introduces WebCode2M, a new dataset comprising 2.56 million instances, each containing a design image along with the corresponding webpage code and layout details. Sourced from real-world web resources, WebCode2M offers a rich and valuable dataset for webpage code generation across a variety of applications. The dataset quality is ensured by a scoring model that filters out instances with aesthetic deficiencies or other incomplete elements. To validate the effectiveness of WebCode2M, we introduce a baseline model based on the Vision Transformer (ViT), named WebCoder, and establish a benchmark for fair comparison. Additionally, we introduce a new metric, TreeBLEU, to measure the structural hierarchy recall. The benchmarking results demonstrate that our dataset significantly improves the ability of MLLMs to generate code from webpage designs, confirming its effectiveness and usability for future applications in front-end design tools. Finally, we highlight several practical challenges introduced by our dataset, calling for further research. The code and dataset are publicly available at our project homepage: https://***. Copyright © 2024, The Authors. All rights reserved.

关键词： Web Design

Scientific data Lake for High Luminosity LHC project and other data-intensive particle and astro-particle physics experiments 5

学校读者我要写书评

暂无评论

Scientific Data Lake for High Luminosity LHC project and oth...

5th International Conference on Particle Physics and Astrophysics, ICPPA 2020

作者： Alekseev, A. Kiryanov, A. Klimentov, A. Korchuganova, T. Mitsyn, V. Oleynik, D. Smirnov, A. Smirnov, S. Zarochentsev, A. Compiler Technology Department Ivannikov Institute for System Programming of the Ras Moscow109004 Russia Cloud Technologies and Big Data Analytics Laboratory Plekhanov Russian University of Economics Moscow117997 Russia Atlas Group Universidad Andres Bello Santiago7550196 Chile Department of Computing Resources and Technologies Nrc "kurchatov Institute"-PNPI Gatchina188300 Russia Physics Department Brookhaven National Laboratory UptonNY11973 United States Laboratory of Information Technologies Joint Institute for Nuclear Research Dubna141980 Russia Institute of Nuclear Physics and Engineering National Research Nuclear University MEPhI Moscow115409 Russia Laboratory of Ultra-High Energy Physics Saint Petersburg State University Saint Petersburg198504 Russia

The next phase of LHC Operations-High Luminosity LHC (HL-LHC), which is aimed at ten-fold increase in the luminosity of proton-proton collisions at the energy of 14 TeV, is expected to start operation in 2027-2028 and will deliver an unprecedented scientific data volume of multi-exabyte scale. This amount of data has to be stored and the corresponding storage system should ensure fast and reliable data delivery for processing by scientific groups distributed all over the world. The present LHC computing and data processing model will not be able to provide the required infrastructure growth even taking into account the expected hardware technology evolution. To address this challenge the new state-of-The-Art computing infrastructure technologies are now being developed and are presented here. The possibilities of application of the HL-LHC distributed data handling technique for other particle and astro-particle physics experiments dealing with large-scale data volumes like DUNE, LSST, Belle-II, JUNO, SKAO etc. are also discussed. © Published under licence by IOP Publishing Ltd.

关键词： Luminance

Unique in the Metro system: The Likelihood to Re-Identify a Metro User with Limited Trajectory Points

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Yang, Hongtai Ping, An Wei, Hongmin Zhai, Guocong School of Transportation and Logistics Institute of System Science and Engineering National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu611756 China Guangdong–Hong Kong-Macau Joint Laboratory for Smart Cities Shenzhen518060 China School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu611756 China Department of Civil & Environmental Engineering Old Dominion University 129C Kaufman Hall NorfolkVA23529 United States

Though the collection of metro smart card data could help improve the operations of the metro system, the release of such data might lead to privacy issues. Few studies have quantified the probability to re-identify a user from the smart card data using very limited trajectory points. Thus, this study investigates this topic by analyzing eight-day metro smart card data of Chengdu, China. Results reveal that, on the macro level, three random trajectory points with a temporal resolution of one minute and one hour are enough to identify over 90% and 67% of the users. Even when the resolution is reduced to one day, 20% of the users could be still be identified by three points. On the individual level, three carefully selected points with a temporal resolution of one minute, one hour, and one day could lead to a re-identification risk no less than 0.5 for 99%, 89%, and 52% of the users. The effects of number of points, number of users, and other temporal resolutions are also thoroughly evaluated. These findings emphasize the great privacy issues involved in the release of metro smart card data and remind metro operators to take proactive measures to enhance privacy protection. © 2023, The Authors. All rights reserved.

关键词： Smart cards

SpirDet: Towards Efficient, Accurate and Lightweight Infrared Small Target Detector

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Mao, Qianchen Li, Qiang Wang, Bingshu Zhang, Yongjun Dai, Tao Chen, C.L. Philip The School of Software Northwestern Polytechnical University Taicang Campus Suzhou215400 China The School of Software Northwestern Polytechnical University Xi’an710129 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China The College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China The School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou510641 China

In recent years, the detection of infrared small targets using deep learning methods has garnered substantial attention due to notable advancements. To improve the detection capability of small targets, these methods commonly maintain a pathway that preserves high-resolution features of sparse and tiny targets. However, it can result in redundant and expensive computations. To tackle this challenge, we propose SpirDet, a novel approach for efficient detection of infrared small targets. Specifically, to cope with the computational redundancy issue, we employ a new dual-branch sparse decoder to restore the feature map. Firstly, the fast branch directly predicts a sparse map indicating potential small target locations (occupying only 0.5% area of the map). Secondly, the slow branch conducts fine-grained adjustments at the positions indicated by the sparse map. Additionally, we design an lightweight DO-RepEncoder based on reparameterization with the Downsampling Orthogonality, which can effectively reduce memory consumption and inference latency. Extensive experiments show that the proposed SpirDet significantly outperforms state-of-the-art models while achieving faster inference speed and fewer parameters. For example, on the IRSTD-1K dataset, SpirDet improves MIoU by 4.7 and has a 7× FPS acceleration compared to the previous state-of-the-art model. The code will be open to the public. © 2024, CC BY.

关键词： Deep learning

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liao, Hao Liu, Ming-Kai Mariani, Manuel Sebastian Zhou, Mingyang Wu, Xingtong National Engineering Laboratory for Big Data System Computing Technology Guangdong Province Key Laboratory of Popular High Performance Computers College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu610051 China URPP Social Networks Universität Zürich CH-8050 Switzerland

When investigating the spreading of a piece of information or the diffusion of an innovation, we often lack information on the underlying propagation network. Reconstructing the hidden propagation paths based on the observed diffusion process is a challenging problem which has recently attracted attention from diverse research fields. To address this reconstruction problem, based on static similarity metrics commonly used in the link prediction literature, we introduce new node-node temporal similarity metrics. The new metrics take as input the time-series of multiple independent spreading processes, based on the hypothesis that two nodes are more likely to be connected if they were often infected at similar points in time. This hypothesis is implemented by introducing a time-lag function which penalizes distant infection times. We find that the choice of this time-lag strongly affects the metrics' reconstruction accuracy, depending on the network's clustering coefficient and we provide an extensive comparative analysis of static and temporal similarity metrics for network reconstruction. Our findings shed new light on the notion of similarity between pairs of nodes in complex networks. Copyright © 2019, The Authors. All rights reserved.

关键词： Information services

EFFICIENTLY PARAMETERIZED NEURAL METRIPLECTIC systemS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Gruber, Anthony Lee, Kookjin Lim, Haksoo Park, Noseong Trask, Nathaniel Center for Computing Research Sandia National Laboratories AlbuquerqueNM United States School of Computing and Augmented Intelligence Arizona State University TempeAZ United States Big Data Analytics Laboratory Yonsei University Seoul Korea Republic of Big Data Analytics Laboratory Korea Advanced Institute of Science and Technology Daejeon Korea Republic of School of Engineering and Applied Science University of Pennsylvania PhiladelphiaPA United States

Metriplectic systems are learned from data in a way that scales quadratically in both the size of the state and the rank of the metriplectic data. Besides being provably energy conserving and entropy stable, the proposed approach comes with approximation results demonstrating its ability to accurately learn metriplectic dynamics from data as well as an error estimate indicating its potential for generalization to unseen timescales when approximation error is low. Examples are provided which illustrate performance in the presence of both full state information as well as when entropic variables are unknown, confirming that the proposed approach exhibits superior accuracy and scalability without compromising on model expressivity. Copyright © 2024, The Authors. All rights reserved.

关键词：