检索结果-内蒙古大学图书馆

DeePMD-kit v3: A Multiple-Backend Framework for Machine Learning Potentials

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zeng, Jinzhe Zhang, Duo Peng, Anyang Zhang, Xiangyu He, Sensen Wang, Yan Liu, Xinzijian Bi, Hangrui Li, Yifan Cai, Chun Zhang, Chengqian Du, Yiming Zhu, Jia-Xin Mo, Pinghui Huang, Zhengtao Zeng, Qiyu Shi, Shaochen Qin, Xuejian Yu, Zhaoxi Luo, Chenxing Ding, Ye Liu, Yun-Pei Shi, Ruosong Wang, Zhenyu Bore, Sigbjørn Løland Chang, Junhan Deng, Zhe Ding, Zhaohan Han, Siyuan Jiang, Wanrun Ke, Guolin Liu, Zhaoqing Lu, Denghui Muraoka, Koki Oliaei, Hananeh Singh, Anurag Kumar Que, Haohui Xu, Weihong Xu, Zhangmancang Zhuang, Yong-Bin Dai, Jiayu Giese, Timothy J. Jia, Weile Xu, Ben York, Darrin M. Zhang, Linfeng Wang, Han School of Artificial Intelligence and Data Science Unversity of Science and Technology of China Hefei China AI for Science Institute Beijing100080 China DP Technology Beijing100080 China Academy for Advanced Interdisciplinary Studies Peking University Beijing100871 China State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing100871 China University of Chinese Academy of Sciences Beijing China Baidu Inc. Beijing China Department of Computer Science University of Toronto TorontoON Canada Department of Chemistry Princeton University PrincetonNJ08540 United States University of Chinese Academy of Sciences Beijing100871 China State Key Laboratory of Physical Chemistry of Solid Surfaces iChEM College of Chemistry and Chemical Engineering Xiamen University Xiamen361005 China College of Integrated Circuits Hunan University Changsha410082 China State Key Laboratory of Advanced Technology for Materials Synthesis and Processing Center for Smart Materials and Device Integration School of Material Science and Engineering Wuhan University of Technology Wuhan430070 China College of Science National University of Defense Technology Changsha410073 China Hunan Key Laboratory of Extreme Matter and Applications National University of Defense Technology Changsha410073 China ByteDance Research Beijing100098 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Ningbo315201 China College of Materials Science and Opto-Electronic Technology University of Chinese Academy of Sciences Beijing100049 China Key Laboratory of Theoretical and Computational Photochemistry of Ministry of Education College of Chemistry Beijing Normal University Beijing100875 China Department of Geosciences Princeton University PrincetonNJ08544 United States Department of Applied Physics and Applied Mathematics Columbia University New YorkNY10027 United States IKKEM Fujian Xiamen361005 China Graduate

In recent years, machine learning potentials (MLPs) have become indispensable tools in physics, chemistry, and materials science, driving the development of software packages for molecular dynamics (MD) simulations and related applications. These packages, typically built on specific machine learning frameworks such as TensorFlow, PyTorch, or JAX, face integration challenges when advanced applications demand communication across different frameworks. The previous TensorFlow-based implementation of DeePMD-kit exemplified these limitations. In this work, we introduce DeePMD-kit version 3, a significant update featuring a multi-backend framework that supports TensorFlow, PyTorch, JAX, and PaddlePaddle backends, and demonstrate the versatility of this architecture through the integration of other MLPs packages and of Differentiable Molecular Force Field. This architecture allows seamless backend switching with minimal modifications, enabling users and developers to integrate DeePMD-kit with other packages using different machine learning frameworks. This innovation facilitates the development of more complex and interoperable workflows, paving the way for broader applications of MLPs in scientific research. Copyright © 2025, The Authors. All rights reserved.

关键词： Molecular dynamics

A Mixing Time Lower Bound for a Simplified Version of BART

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Ronen, Omer Saarinen, Theo Tan, Yan Shuo Duncan, James Yu, Bin Department of Statistics UC Berkeley United States Department of Electrical Engineering and Computer Sciences UC Berkeley United States Center for Computational Biology UC Berkeley United States Department of Statistics and Data Science National University of Singapore Singapore Microsoft Research United States Group in Biostatistics UC Berkeley United States

Bayesian Additive Regression Trees (BART) is a popular Bayesian non-parametric regression algorithm. The posterior is a distribution over sums of decision trees, and predictions are made by averaging approximate samples from the posterior. The combination of strong predictive performance and the ability to provide uncertainty measures has led BART to be commonly used in the social sciences, biostatistics, and causal inference. BART uses Markov Chain Monte Carlo (MCMC) to obtain approximate posterior samples over a parameterized space of sums of trees, but it has often been observed that the chains are slow to mix. In this paper, we provide the first lower bound on the mixing time for a simplified version of BART in which we reduce the sum to a single tree and use a subset of the possible moves for the MCMC proposal distribution. Our lower bound for the mixing time grows exponentially with the number of data points. Inspired by this new connection between the mixing time and the number of data points, we perform rigorous simulations on BART. We show qualitatively that BART’s mixing time increases with the number of data points. The slow mixing time of the simplified BART suggests a large variation between different runs of the simplified BART algorithm and a similar large variation is known for BART in the literature. This large variation could result in a lack of stability in the models, predictions and posterior intervals obtained from the BART MCMC samples. Our lower bound and simulations suggest increasing the number of chains with the number of data points. Copyright © 2022, The Authors. All rights reserved.

关键词： Decision trees

Gillespie algorithms for stochastic multiagent dynamics in populations and networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Masuda, Naoki Vestergaard, Christian L. Department of Mathematics State University of New York at Buffalo NY United States Computational and Data-Enabled Science and Engineering Program State University of New York at Buffalo NY United States Decision and Bayesian Computation Department of Neuroscience Cnrs Umr 3571 Department of Computational Biology Cnrs Usr 3756 Institut Pasteur Paris France

Many multiagent dynamics, including various collective dynamics occurring on networks, can be modeled as a stochastic process in which the agents in the system change their state over time in interaction with each other. The Gillespie algorithms are popular algorithms that exactly simulate such stochastic multiagent dynamics when each state change is driven by a discrete event, the dynamics is defined in continuous time, and the stochastic law of event occurrence is governed by independent Poisson processes. In the first main part of this volume, we provide a tutorial on the Gillespie algorithms focusing on simulation of social multiagent dynamics occurring in populations and networks. We do not assume advanced knowledge of mathematics (or computer science or physics). We clarify why one should use the continuous-time models and the Gillespie algorithms in many cases, instead of easier-to-understand discrete-time models. In the remainder of this volume, we review recent extensions of the Gillespie algorithms aiming to add more reality to the model (i.e., non-Poissonian cases) or to speed up the simulations. © 2021, CC BY.

关键词： Stochastic systems

Artificial intelligence for modelling infectious disease epidemics

学校读者我要写书评

暂无评论

Nature 2025年第8051期638卷 623-635页

作者： Kraemer, Moritz U. G. Tsui, Joseph L.-H. Chang, Serina Y. Lytras, Spyros Khurana, Mark P. Vanderslott, Samantha Bajaj, Sumali Scheidwasser, Neil Curran-Sebastian, Jacob Liam Semenova, Elizaveta Zhang, Mengyan Unwin, H. Juliette T. Watson, Oliver J. Mills, Cathal Dasgupta, Abhishek Ferretti, Luca Scarpino, Samuel V. Koua, Etien Morgan, Oliver Tegally, Houriiyah Paquet, Ulrich Moutsianas, Loukas Fraser, Christophe Ferguson, Neil M. Topol, Eric J. Duchêne, David A. Stadler, Tanja Kingori, Patricia Parker, Michael J. Dominici, Francesca Shadbolt, Nigel Suchard, Marc A. Ratmann, Oliver Flaxman, Seth Holmes, Edward C. Gomez-Rodriguez, Manuel Schölkopf, Bernhard Donnelly, Christl A. Pybus, Oliver G. Cauchemez, Simon Bhatt, Samir Pandemic Sciences Institute University of Oxford Oxford United Kingdom Department of Biology University of Oxford Oxford United Kingdom Department of Electrical Engineering and Computer Science University of California Berkeley Berkeley CA United States UCSF UC Berkeley Joint Program in Computational Precision Health Berkeley CA United States Division of Systems Virology Department of Microbiology and Immunology The Institute of Medical Science The University of Tokyo Tokyo Japan Section of Epidemiology Department of Public Health University of Copenhagen Copenhagen Denmark Oxford Vaccine Group University of Oxford and NIHR Oxford Biomedical Research Centre Oxford United Kingdom Department of Epidemiology and Biostatistics Imperial College London London United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom School of Mathematics University of Bristol Bristol United Kingdom MRC Centre for Global Infectious Disease Analysis School of Public Health Imperial College London London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Doctoral Training Centre University of Oxford Oxford United Kingdom Institute for Experiential AI Northeastern University MA Boston Thailand Santa Fe Institute Santa Fe NM United States World Health Organization Regional Office for Africa Brazzaville Congo WHO Hub for Pandemic and Epidemic Intelligence Health Emergencies Programme World Health Organization Berlin Germany Centre for Epidemic Response and Innovation (CERI) School for Data Science and Computational Thinking Stellenbosch University Stellenbosch South Africa African Institute for Mathematical Sciences (AIMS) South Africa Muizenberg Cape Town South Africa Genomics England London United Kingdom Scripps Research La Jolla CA United States Department of Biosystems Science and Engineering ETH Zürich Basel Switzerland Swiss Institute of Bioinformatics Lausanne Switzerland The Ethox Centre Nuffield

Infectious disease threats to individual and public health are numerous, varied and frequently unexpected. Artificial intelligence (AI) and related technologies, which are already supporting human decision making in economics, medicine and social science, have the potential to transform the scope and power of infectious disease epidemiology. Here we consider the application to infectious disease modelling of AI systems that combine machine learning, computational statistics, information retrieval and data science. We first outline how recent advances in AI can accelerate breakthroughs in answering key epidemiological questions and we discuss specific AI methods that can be applied to routinely collected infectious disease surveillance data. Second, we elaborate on the social context of AI for infectious disease epidemiology, including issues such as explainability, safety, accountability and ethics. Finally, we summarize some limitations of AI applications in this field and provide recommendations for how infectious disease epidemiology can harness most effectively current and future developments in AI. © Springer Nature Limited 2025.

关键词：

K-Core Decomposition on Super Large Graphs with Limited Resources

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Gao, Shicheng Xu, Jie Li, Xiaosen Fu, Fangcheng Zhang, Wentao Ouyang, Wen Tao, Yangyu Cui, Bin School of Electronic and Computer Engineering Shenzhen Graduate School Peking University China Tencent Inc. China Center for Data Science Peking University National Engineering Laboratory for Big Data Analysis and Applications China School of CS Key Laboratory of High Confidence Software Technologies Peking University China Institute of Computational Social Science Peking University Qingdao China

K-core decomposition is a commonly used metric to analyze graph structure or study the relative importance of nodes in complex graphs. Recent years have seen rapid growth in the scale of the graph, especially in industrial settings. For example, our industrial partner runs popular social applications with billions of users and is able to gather a rich set of user data. As a result, applying K-core decomposition on large graphs has attracted more and more attention from academics and the industry. A simple but effective method to deal with large graphs is to train them in the distributed settings, and some distributed K-core decomposition algorithms are also proposed. Despite their effectiveness, we experimentally and theoretically observe that these algorithms consume too many resources and become unstable on super-large-scale graphs, especially when the given resources are limited. In this paper, we deal with those super-large-scale graphs and propose a divide-and-conquer strategy on top of the distributed K-core decomposition algorithm. We evaluate our approach on three large graphs. The experimental results show that the consumption of resources can be significantly reduced, and the calculation on large-scale graphs becomes more stable than the existing methods. For example, the distributed K-core decomposition algorithm can scale to a large graph with 136 billion edges without losing correctness with our divide-and-conquer technique. Copyright © 2021, The Authors. All rights reserved.

关键词： Graphic methods

DeepCare: Deep Learning-Based Smart Healthcare Framework using 5G Assisted Network Slicing

学校读者我要写书评

暂无评论

DeepCare: Deep Learning-Based Smart Healthcare Framework usi...

International Symposium on Advanced Networks and Telecommunication Systems (ANTS)

作者： Deborsi Basu Vikram Krishnakumar Uttam Ghosh Raja Datta G. S. Sanyal School of Telecommunications Indian Institute of Technology Kharagpur India Dept. of Electronics and Communication Engineering SASTRA Deemed Univ. Thanjavur Tamil Nadu India Dept. of Data Science and Computer Science School of Applied Computational Sciences MMC USA Dept. of Electronics and Electrical Comm. Engg. Indian Institute of Technology Kharagpur India

ISBN: (数字)9781665473408

ISBN: (纸本)9781665473415

5G and beyond communication networks require satisfying very low latency standards, high reliability, high-speed user connectivity, more security, improved capacity and better service demands. Augmenting such a wide range of KPIs (Key Performance Indicators) needs a smart, intelligent and programmable solution for TSPs (Telecommunication Service Providers). Resource availability and quality sustainability are challenging parameters in a heterogeneous 5G environment. Programmable Dynamic Network Slicing (PDNS) is a key technology enabling parameter that can allow multiple tenants to bring their versatile applications simultaneously over shared physical infrastructure. Latest emerging technologies like virtualized Software-Defined Networks (vSDN) and Artificial Intelligence (AI) play a pivotal supporting role in solving the above-mentioned constraints. Using the PDNS framework, we have proposed a novel slice backup algorithm leveraging Deep Learning (DL) neural network to orchestrate network latency and load efficiently. Our model has been trained using the available KPIs and incoming traffic is analyzed. The proposed solution performs stable load balancing between shared slices even if certain extreme conditions (slice unavailability) through intelligent resource allocation. The framework withstands service outage and always select the most suitable slice as a backup. Our results show latency-aware resource distribution for better network stability.

关键词： 5G mobile communication Network slicing Stability criteria Resource management Telecommunication network reliability Artificial intelligence Sustainable development

Evaluation of tree based regression over multiple linear regression for non-normally distributed data in battery performance

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Chowdhury, Shovan Lin, Yuxiao Liawc, Boryann Kerby, Leslie Department of Mechanical Engineering Idaho State University PocatelloID83209 United States Materials Science and Engineering Energy and Environment Science and Technology Idaho National Laboratory Idaho FallsID83415 United States Energy Storage and Advanced Transportation Energy and Environment Science and Technology Idaho National Laboratory Idaho FallsID83415 United States Computational Engineering and Data Science Laboratory Department of Computer Science Idaho State University PocatelloID83209 United States

Battery performance datasets are typically non-normal and multicollinear. Extrapolating such datasets for model predictions needs attention to such characteristics. This study explores the impact of data normality in building machine learning models. In this work, tree-based regression models and multiple linear regressions models are each built from a highly skewed non-normal dataset with multicollinearity and compared. Several techniques are necessary, such as data transformation, to achieve a good multiple linear regression model with this dataset;the most useful techniques are discussed. With these techniques, the best multiple linear regression model achieved an R2 = 81.23% and exhibited no multicollinearity effect for the dataset used in this study. Tree-based models perform better on this dataset, as they are non-parametric, capable of handling complex relationships among variables and not affected by multicollinearity. We show that bagging, in the use of Random Forests, reduces overfitting. Our best tree-based model achieved accuracy of R2 = 97.73%. This study explains why tree-based regressions promise as a machine learning model for non-normally distributed, multicollinear data. © 2021, CC BY.

关键词： Decision trees

A Modified Clustering Using Representatives to Enhance and Optimize Tracking and Monitoring of Maritime Traffic in Real-time Using Automatic Identification System data

学校读者我要写书评

暂无评论

A Modified Clustering Using Representatives to Enhance and O...

International Conference on computational science and computational Intelligence (CSCI)

作者： Cheronika Manyfield-Donald Tor A. Kwembe Jing-Ru C. Cheng Computational Data-Enabled Science and Engineering Jackson State University Jackson MS USA Department of Mathematics and Statistical Sciences Jackson State University Jackson MS USA Information Technology Lab. Engineer Research and Development Center U.S. Army Corps of Engineers Vicksburg MS USA

ISBN: (纸本)9781665458429

In this paper, we introduce a modification of the Clustering Using Representatives (CURE) algorithm to enhance and optimize the tracking and monitoring of maritime traffic in real-time using the Automatic Identification System (AIS) data. In doing so, we present a 2-D points data collection system for the utilization of a modified unsupervised machine learning clustering method of the CURE algorithm integrated with a data streaming algorithm to develop a more efficient method that will directly assist in adverting accidents and support in vessels avoiding dangerous environments. Results are presented that show tracking in inland as well as open sea waterways.

关键词： Machine learning algorithms Tracking Scientific computing Clustering methods Clustering algorithms Machine learning data collection

End-to-end AI Framework for Interpretable Prediction of Molecular and Crystal Properties

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Park, Hyun Zhu, Ruijie Huerta, E.A. Chaudhuri, Santanu Tajkhorshid, Emad Cooper, Donny Theoretical and Computational Biophysics Group Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign UrbanaIL61801 United States Department of Materials Science and Engineering Northwestern University EvanstonIL60208 United States Data Science and Learning Division Argonne National Laboratory LemontIL60439 United States Department of Computer Science The University of Chicago ChicagoIL60637 United States Department of Physics University of Illinois at Urbana-Champaign UrbanaIL61801 United States Multiscale Materials and Manufacturing Lab University of Illinois Chicago ChicagoIL60607 United States Department of Biochemistry University of Illinois at Urbana-Champaign UrbanaIL61801 United States Center for Biophysics and Quantitative Biology University of Illinois at Urbana-Champaign UrbanaIL61801 United States Computational Science and Engineering Data Science and AI Department TotalEnergies EP Research & Technology USA LLC HoustonTX77002 United States

We introduce an end-to-end computational framework that allows for hyperparameter optimization using the DeepHyper library, accelerated model training, and interpretable AI inference. The framework is based on state-of-the-art AI models including CGCNN, PhysNet, SchNet, MPNN, MPNN-transformer, and TorchMD-NET. We employ these AI models along with the benchmark QM9, hMOF, and MD17 datasets to showcase how the models can predict user-specified material properties within modern computing environments. We demonstrate transferable applications in the modeling of small molecules, inorganic crystals and nanoporous metal organic frameworks with a unified, standalone framework. We have deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and in the Delta supercomputer at the National Center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership-class computing environments. We release these digital assets as open source scientific software in GitLab, and ready-to-use Jupyter notebooks in Google Colab. Copyright © 2022, The Authors. All rights reserved.

关键词： Organometallics