检索结果-内蒙古大学图书馆

A Scalable Real-Time Data Assimilation Framework for Predicting Turbulent Atmosphere Dynamics 24

A Scalable Real-Time Data Assimilation Framework for Predict...

Proceedings of the SC '24 Workshops of the International Conference on High Performance computing, Network, Storage, and Analysis

作者： Junqi Yin Siming Liang Siyan Liu Feng Bao Hristo G. Chipilski Dan Lu Guannan Zhang National Center for Computational Science Oak Ridge National Laboratory Oak Ridge TN USA Department of Mathematics Florida State University Tallahassee FL USA Computational Science and Engineering Division Oak Ridge National Laboratory Oak Ridge TN USA Department of Scientific Computing Florida State University Tallahassee FL USA Computer Science and Mathematics Division Oak Ridge National Laboratory Oak Ridge TN USA

ISBN: (纸本)9798350355543

AI-based foundation models like FourCastNet, GraphCast, ClimaX, and Pangu-Weather are revolutionizing weather and climate predictions but are not yet ready for operational use. Their limitation lies in the absence of a data assimilation system to incorporate real-time Earth system observations, crucial for accurately forecasting events like tropical cyclones and atmospheric rivers. To overcome these obstacles, we introduce a generic real-time data assimilation framework and demonstrate its end-to-end performance on the Frontier supercomputer. This framework comprises two primary modules: an ensemble score filter (EnSF), which significantly outperforms the state-of-the-art data assimilation method, e.g., the Local Ensemble Transform Kalman Filter (LETKF); and a vision transformer-based surrogate capable of real-time adaptation through the integration of observational data. We demonstrate both the strong and weak scaling of our framework up to 1024 GPUs on the Exascale supercomputer, Frontier. Our results not only illustrate the framework's exceptional scalability on high-performance computing systems, but also demonstrate the importance of supercomputers in real-time data assimilation for weather and climate predictions. Even though the proposed framework is tested only on a benchmark surface quasi-geostrophic (SQG) turbulence system, it has the potential to be combined with existing AI-based foundation models, making it suitable for future operational implementations.

关键词： Diffusion models

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning for Cellular VR: Online Learning and Dynamic Caching

arXiv

引用

arXiv 2025年

作者： Tharakan, Krishnendu S. Dahrouj, Hayssam Kouzayha, Nour ElSawy, Hesham Al-Naffouri, Tareq Y. The School of Computing Queen's University Kingston Canada The Department of Electrical Engineering University of Sharjah Sharjah United Arab Emirates The Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

Delivering an immersive experience to virtual reality (VR) users through wireless connectivity offers the freedom to engage from anywhere at any time. Nevertheless, it is challenging to ensure seamless wireless connectivity that delivers real-time and high-quality videos to the VR users. This paper proposes a field of view (FoV) aware caching for mobile edge computing (MEC)-enabled wireless VR network. In particular, the FoV of each VR user is cached/prefetched at the base stations (BSs) based on the caching strategies tailored to each BS. Specifically, decentralized and personalized federated learning (DP-FL) based caching strategies with guarantees are presented. Considering VR systems composed of multiple VR devices and BSs, a DP-FL caching algorithm is implemented at each BS to personalize content delivery for VR users. The utilized DP-FL algorithm guarantees a probably approximately correct (PAC) bound on the conditional average cache hit. Further, to reduce the cost of communicating gradients, one-bit quantization of the stochastic gradient descent (OBSGD) is proposed, and a convergence guarantee of O(1/√T) is obtained for the proposed algorithm, where T is the number of iterations. Additionally, to better account for the wireless channel dynamics, the FoVs are grouped into multicast or unicast groups based on the number of requesting VR users. The performance of the proposed DP-FL algorithm is validated through realistic VR head-tracking dataset, and the proposed algorithm is shown to have better performance in terms of average delay and cache hit as compared to baseline algorithms. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Robustness of graph embedding methods for community detection

arXiv

引用

arXiv 2024年

作者： Wei, Zhi-Feng Moriano, Pablo Kannan, Ramakrishnan Advanced Computing Mathematics and Data Division Pacific Northwest National Laboratory RichlandWA99354 United States Department of Mathematics Indiana University BloomingtonIN47405 United States Computer Science and Mathematics Division Oak Ridge National Laboratory Oak RidgeTN37830 United States

This study investigates the robustness of graph embedding methods for community detection in the face of network perturbations, specifically edge deletions. Graph embedding techniques, which represent nodes as low-dimensional vectors, are widely used for various graph machine learning tasks due to their ability to capture structural properties of networks effectively. However, the impact of perturbations on the performance of these methods remains relatively understudied. The research considers state-of-the-art graph embedding methods from two families: matrix factorization (e.g., LE, LLE, HOPE, M-NMF) and random walk-based (e.g., DeepWalk, LINE, node2vec). Through experiments conducted on both synthetic and real-world networks, the study reveals varying degrees of robustness within each family of graph embedding methods. The robustness is found to be influenced by factors such as network size, initial community partition strength, and the type of perturbation. Notably, node2vec and LLE consistently demonstrate higher robustness for community detection across different scenarios, including networks with degree and community size heterogeneity. These findings highlight the importance of selecting an appropriate graph embedding method based on the specific characteristics of the network and the task at hand, particularly in scenarios where robustness to perturbations is crucial. Copyright © 2024, The Authors. All rights reserved.

关键词： Graph embeddings

来源：评论

学校读者我要写书评

暂无评论

Tensor neural networks for high-dimensional Fokker-Planck equations

arXiv

引用

arXiv 2024年

作者： Wang, Taorui Hu, Zheyuan Kawaguchi, Kenji Zhang, Zhongqiang Karniadakis, George Em Department of Mathematical Sciences Worcester Polytechnic Institute WorcesterMA United States Department of Computer Science National University of Singapore 119077 Singapore Division of Applied Mathematics Brown University ProvidenceRI02912 United States Advanced Computing Mathematics and Data Division Pacific Northwest National Laboratory RichlandWA United States

We solve high-dimensional steady-state Fokker-Planck equations on the whole space by applying tensor neural networks. The tensor networks are a linear combination of tensor products of one-dimensional feedforward networks or a linear combination of several selected radial basis functions. The use of tensor feedforward networks allows us to efficiently exploit auto-differentiation (in physical variables) in major Python packages while using radial basis functions can fully avoid auto-differentiation, which is rather expensive in high dimensions. We then use the physics-informed neural networks and stochastic gradient descent methods to learn the tensor networks. One essential step is to determine a proper bounded domain or numerical support for the Fokker-Planck equation. To better train the tensor radial basis function networks, we impose some constraints on parameters, which lead to relatively high accuracy. We demonstrate numerically that the tensor neural networks in physics-informed machine learning are efficient for steady-state Fokker-Planck equations from two to ten dimensions. Copyright © 2024, The Authors. All rights reserved.

关键词： Radial basis function networks

来源：评论

学校读者我要写书评

暂无评论

Explainable Enrichment-Driven GrAph Reasoner (EDGAR) for Large Knowledge Graphs with Applications in Drug Repurposing

arXiv

引用

arXiv 2024年

作者： Olasunkanmi, Olawumi Morris, Evan Kebede, Yaphet Lee, Harlin Ahalt, Stanley C. Tropsha, Alexander Bizon, Chris Department of Computer Science United States Renaissance Computing Institute United States School of Data Science and Society United States Division of Chemical Biology and Medicinal Chemistry UNC Eshelman School of Pharmacy University of North Carolina at Chapel Hill Chapel HillNC United States

Knowledge graphs (KGs) represent the connections and relationships between real-world entities. We propose a link prediction framework on KGs named Enrichment-Driven GrAph Reasoner (EDGAR) that infers new edges by mining entity-local rules. This approach is based on enrichment analysis, a well-established statistical method used to calculate mechanisms common to a set of differentially expressed genes. EDGAR's inference results are inherently explainable and rankable, equipped with p-values for statistical significance of each enrichment-based rule. We demonstrate its effectiveness on a large-scale biomedical KG, ROBOKOP, focusing on drug repurposing for Alzheimer disease (AD) as a case study. Initially, we extracted 14 known drugs from the KG and identified 20 contextual biomarkers through enrichment analysis, shedding light on functional pathways relevant to the shared efficacy of drugs for AD. Subsequently, using the top 1,000 enrichment results, our enrichment-driven system identified 1,246 additional drug candidates for AD treatment. We validated the top 10 candidates using medical literature evidence. EDGAR is deployed within ROBOKOP, along with a web user interface. This is the first work to use enrichment analysis for either large graph completion or drug *** Codes 68P20 © 2024, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Touchstone benchmark: are we on the right way for evaluating AI algorithms for medical segmentation? 24

Touchstone benchmark: are we on the right way for evaluating...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Pedro R. A. S. Bassi Wenxuan Li Yucheng Tang Fabian Isensee Zifu Wang Jieneng Chen Yu-Cheng Chou Saikat Roy Yannick Kirchhoff Maximilian Rokuss Ziyan Huang Jin Ye Junjun He Tassilo Wald Constantin Ulrich Michael Baumgartner Klaus H. Maier-Hein Paul Jaeger Yiwen Ye Yutong Xie Jianpeng Zhang Ziyang Chen Yong Xia Zhaohu Xing Lei Zhu Yousef Sadegheih Afshin Bozorgpour Pratibha Kumari Reza Azad Dorit Merhof Pengcheng Shi Ting Ma Yuxin Du Fan Bai Tiejun Huang Bo Zhao Haonan Wang Xiaomeng Li Hanxue Gu Haoyu Dong Jichen Yang Maciej A. Mazurowski Saumya Gupta Linshan Wu Jiaxin Zhuang Hao Chen Holger Roth Daguang Xu Matthew B. Blaschko Sergio Decherchi Andrea Cavalli Alan L. Yuille Zongwei Zhou Department of Computer Science Johns Hopkins University and Department of Pharmacy and Biotechnology University of Bologna and Center for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia Department of Computer Science Johns Hopkins University NVIDIA Division of Medical Image Computing German Cancer Research Center (DKFZ) and Helmholtz Imaging German Cancer Research Center (DKFZ) ESAT-PSI KU Leuven Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University and HIDSS4Health - Helmholtz Information and Data Science School for Health Shanghai Jiao Tong University Shanghai Artificial Intelligence Laboratory Division of Medical Image Computing German Cancer Research Center (DKFZ) Division of Medical Image Computing German Cancer Research Center (DKFZ) and Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Helmholtz Imaging German Cancer Research Center (DKFZ) and Interactive Machine Learning Group (IML) DKFZ School of Computer Science and Engineering Northwestern Polytechnical University Australian Institute for Machine Learning The University of Adelaide College of Computer Science and Technology Zhejiang University Hong Kong University of Science and Technology (Guangzhou) Hong Kong University of Science and Technology (Guangzhou) and Hong Kong University of Science and Technology Faculty of Informatics and Data Science University of Regensburg Faculty of Electrical Engineering and Information Technology RWTH Aachen University Faculty of Informatics and Data Science University of Regensburg and Fraunhofer Institute for Digital Medicine MEVIS Electronic & Information Engineering School Harbin Institute of Technology (Shenzhen) Shanghai Jiao Tong University and Beijing Academy of Artificial Intelligence (BAAI) S

ISBN: (纸本)9798331314385

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms. In addition, we also evaluated pre-existing AI frameworks—which, differing from algorithms, are more flexible and can support different algorithms—including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Toward efficient resource utilization at edge nodes in federated learning

arXiv

引用

arXiv 2023年

作者： Alawadi, Sadi Ait-Mlouk, Addi Toor, Salman Hellander, Andreas Department of Computer Science Blekinge Institute of Technology Karlskrona Sweden School of Informatics University of Skövde Skövde Sweden Department of Information Technology Division of Scientific Computing Uppsala University Sweden Scaleout Systems Sweden

Federated learning (FL) enables edge nodes to collaboratively contribute to constructing a global model without sharing their data. This is accomplished by devices computing local, private model updates that are then aggregated by a server. However, computational resource constraints and network communication can become a severe bottleneck for larger model sizes typical for deep learning (DL) applications. Edge nodes tend to have limited hardware resources (RAM, CPU), and the network bandwidth and reliability at the edge is a concern for scaling federated fleet applications. In this paper, we propose and evaluate a FL strategy inspired by transfer learning in order to reduce resource utilization on devices, as well as the load on the server and network in each global training round. For each local model update, we randomly select layers to train, freezing the remaining part of the model. In doing so, we can reduce both server load and communication costs per round by excluding all untrained layer weights from being transferred to the server. The goal of this study is to empirically explore the potential trade-off between resource utilization on devices and global model convergence under the proposed strategy. We implement the approach using the FL framework FEDn. A number of experiments were carried out over different datasets (CIFAR-10, CASA, and IMDB), performing different tasks using different DL model architectures. Our results show that training the model partially can accelerate the training process, efficiently utilizes resources on-device, and reduce the data transmission by around 75% and 53% when we train 25%, and 50% of the model layers, respectively, without harming the resulting global model accuracy. Furthermore, our results demonstrate a negative correlation between the number of participating clients in the training process and the number of layers that need to be trained on each client’s side. As the number of clients increases, there is a decrease

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Fused Fuzzy Deep Learning and Information Steganography for Privacy Preservation in Medical Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Chen, Jingxue Zhao, Pengbiao Deng, Erqiang Khan, Fazlullah Alturki, Ryan Alshawi, Bandar Xiong, Hu School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China the School of Computer Science Faculty of Science and Engineering University of Nottingham Ningbo China Zhejiang Ningbo315104 China the KKR and KSR institute of technology and sciences Andhra Pradesh Guntur India the Division of Research and Development Lovely Professional University Phagwara India the University Centre of Research and Development Chandigarh University Mohali India the Department of Computer and Network Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia the Department of Software Engineering College of Computing Umm Al-Qura University Makkah Saudi Arabia

—Medical Consumer Electronics (MCE) have greatly facilitated people’s lives, allowing patients to obtain personal medical information including medical images. These medical images obtained from MCE need to be processed using segmentation, diagnosis, recognition to obtain useful information. Deep learning plays an important role in medical image segmentation and recognition. However, other personal information about the patient, such as previous cases, is often required to determine the final diagnosis. However, sending personal information and medical images generated through MCE to the clinic directly exposes patient privacy. Therefore, in this paper, we propose a digital medical image privacy protection framework based on information steganography with fuzzy deep learning. The proposed framework transforms patient privacy information into invisible noise and hides it in the deep covert space of the image. This method plays a crucial role in ensuring patient privacy and data security. Furthermore, this method can ensure a high level of image segmentation accuracy that supports the development of personalized medical services. The experimental results show that the proposed framework can embed patient information in medical images without affecting the segmentation task, and effectively protect privacy. Finally, the proposed framework provides new possibilities and impetus for the popularization of MCE. © 2025 IEEE.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Computational Limits of Low-Rank Adaptation (LoRA) for Transformer-Based Models

arXiv

引用

arXiv 2024年

作者： Hu, Jerry Yao-Chieh Su, Maojiang Kuo, En-Jui Song, Zhao Liu, Han Department of Computer Science Northwestern University EvanstonIL60208 United States Department of Information and Computing Science USTC Anhui Hefei230026 China Physics Division National Center for Theoretical Sciences Taipei106319 Taiwan Adobe Research SeattleWA98103 United States Department of Statistics and Data Science Northwestern University EvanstonIL60208 United States

We study the computational limits of Low-Rank Adaptation (LoRA) update for finetuning transformer-based models using fine-grained complexity theory. Our key observation is that the existence of low-rank decompositions within the gradient computation of LoRA adaptation leads to possible algorithmic speedup. This allows us to (i) identify a phase transition behavior and (ii) prove the existence of nearly linear algorithms by controlling the LoRA update computation term by term, assuming the Strong Exponential Time Hypothesis (SETH). For the former, we identify a sharp transition in the efficiency of all possible rank-r LoRA update algorithms for transformers, based on specific norms resulting from the multiplications of the input sequence X, pretrained weights W*, and adapter matrices αBA/r. Specifically, we derive a shared upper bound threshold for such norms, and show that efficient (sub-quadratic) approximation algorithms of LoRA exist only below this threshold. For the latter, we prove the existence of nearly linear approximation algorithms for LoRA adaptation by utilizing the hierarchical low-rank structures of LoRA gradients and approximating the gradients with a series of chained low-rank approximations. To showcase our theory, we consider two practical scenarios: partial (e.g., only WV and WQ) and full adaptations (e.g., WQ, WV, and WK) of weights in attention heads. © 2024, CC BY-NC-SA.

关键词： Approximation algorithms

来源：评论

学校读者我要写书评

暂无评论

A Simulation Study of Quantum Clock Synchronization Using Teleportation

A Simulation Study of Quantum Clock Synchronization Using Te...

引用

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

作者： Eric Yu Anastasia Butko Dipak Ghosal Mariam Kiran Nageswara Rao Department of Computer Science University of California Davis CA Computing Research Division Lawrence Berkeley National Laboratory Berkeley CA Energy Sciences Network (ESnet) Lawrence Berkeley National Laboratory Berkeley CA Computational Sciences and Engineering Division Oak Ridge National Laboratory Oak Ridge TN

ISBN: (数字)9798350366778

ISBN: (纸本)9798350366785

An important requirement in implementing distributed computing and sensing application is the synchronization of clocks at various locations. The Internet relies on the Network Time Protocol (NTP), which synchronizes clocks with accuracy in the order of milliseconds. More recently an ensemble of atomic clocks is used for navigation based on GPS. These clocks are highly accurate and provide time with very low uncertainty. Even so, many physics experiments such as distributed LIGO-based systems may require more accurate clock synchronization that is achievable using quantum entanglement. This requires the deployment of a network of quantum clocks synchronized by exploiting entangled atomic clock qubits. In this paper, we carry out a simulation study of synchronizing a network of quantum clocks interconnected by a fiber plant that supports the ESnet; the latter is used to support the classical communication needed for teleportation. We consider an existing protocol for synchro-nizing the atomic clock qubits that relies on the GHZ states. To assess the performance of the protocol we developed a discrete-event simulation of the network using IBM Qiskit framework for underlying quantum gate operations and measurements. The simulation results shed light on the resources required in terms of the number entangled qubits and the time needed to achieve the synchronization of different number of nodes in ESnet.

关键词： Protocols Accuracy Uncertainty Quantum entanglement Simulation Qubit Teleportation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：