检索结果-内蒙古大学图书馆

Graph Self-Supervised Learning: A Survey

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liu, Yixin Jin, Ming Pan, Shirui Zhou, Chuan Zheng, Yu Xia, Feng Yu, Philip S. Department of Data Science & AI Faculty of IT Monash University VIC3800 Australia Academy of Mathematics and Systems Science Chinese Academy of Sciences China The Department of Computer Science and Information Technology La Trobe University Melbourne Australia School of Engineering Information Technology and Physical Sciences Federation University Australia Department of Computer Science University of Illinois at Chicago ChicagoIL60607-7053 United States

Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field. © 2021, CC BY.

关键词： Graph neural networks

Cosmic-Ray Modulation during Solar Cycles 24-25 Transition Observed with CALET on the International Space Station 38

学校读者我要写书评

暂无评论

Cosmic-Ray Modulation during Solar Cycles 24-25 Transition O...

38th International Cosmic Ray Conference, ICRC 2023

作者： Miyake, Shoko Munakata, Kazuoki Akaike, Yosui Adriani, O. Akaike, Y. Asano, K. Asaoka, Y. Berti, E. Bigongiari, G. Binns, W.R. Bongi, M. Brogi, P. Bruno, A. Cannady, N. Castellini, G. Checchia, C. Cherry, M.L. Collazuol, G. de Nolfo, G.A. Ebisawa, K. Ficklin, A.W. Fuke, H. Gonzi, S. Guzik, T.G. Hams, T. Hibino, K. Ichimura, M. Ioka, K. Ishizaki, W. Israel, M.H. Kasahara, K. Kataoka, J. Kataoka, R. Katayose, Y. Kato, C. Kawanaka, N. Kawakubo, Y. Kobayashi, K. Kohri, K. Krawczynski, H.S. Krizmanic, J.F. Maestro, P. Marrocchesi, P.S. Messineo, A.M. Mitchell, J.W. Miyake, S. Moiseev, A.A. Mori, M. Mori, N. Motz, H.M. Munakata, K. Nakahira, S. Nishimura, J. Okuno, S. Ormes, J.F. Ozawa, S. Pacini, L. Papini, P. Rauch, B.F. Ricciarini, S.B. Sakai, K. Sakamoto, T. Sasaki, M. Shimizu, Y. Shiomi, A. Spillantini, P. Stolzi, F. Sugita, S. Sulaj, A. Takita, M. Tamura, T. Terasawa, T. Torii, S. Tsunesada, Y. Uchihori, Y. Vannuccini, E. Wefel, J.P. Yamaoka, K. Yanagita, S. Yoshida, A. Yoshida, K. Zober, W.V. Ibaraki College Department of Industrial Engineering 866 Nakane Ibaraki Hitachinaka312-8508 Japan Shinshu University Faculty of Science 3-1-1 Asahi Matsumoto Nagano390-8621 Japan Japan Aerospace Exploration Agency EM Utilization Center Human Spaceflight Technology Directorate 2-1-1 Sengen Ibaraki Tsukuba305-8505 Japan Department of Physics University of Florence Via Sansone 1 Sesto Fiorentino50019 Italy INFN Sezione di Firenze Via Sansone 1 Sesto Fiorentino50019 Italy Waseda Research Institute for Science and Engineering Waseda University 17 Kikuicho Shinjuku Tokyo162-0044 Japan JEM Utilization Center Human Spaceflight Technology Directorate Japan Aerospace Exploration Agency 2-1-1 Sengen Ibaraki Tsukuba305-8505 Japan Institute for Cosmic Ray Research The University of Tokyo 5-1-5 Kashiwa-no-Ha Chiba Kashiwa277-8582 Japan Via Madonna del Piano 10 Sesto Fiorentino50019 Italy Department of Physical Sciences Earth and Environment University of Siena via Roma 56 Siena53100 Italy INFN Sezione di Pisa Polo Fibonacci Largo B. Pontecorvo 3 Pisa56127 Italy Department of Physics McDonnell Center for the Space Sciences Washington University One Brookings Drive St. LouisMO63130-4899 United States Heliospheric Physics Laboratory NASA/GSFC GreenbeltMD20771 United States Center for Space Sciences and Technology University of Maryland Baltimore County 1000 Hilltop Circle BaltimoreMD21250 United States Astroparticle Physics Laboratory NASA/GSFC GreenbeltMD20771 United States Center for Research and Exploration in Space Sciences and Technology NASA/GSFC GreenbeltMD20771 United States Department of Physics and Astronomy Louisiana State University 202 Nicholson Hall Baton RougeLA70803 United States Department of Physics and Astronomy University of Padova Via Marzolo 8 Padova35131 Italy INFN Sezione di Padova Via Marzolo 8 Padova35131 Italy Institute of Space and Astronautical Science Japan Aerospace Exploration Agency

We present the solar modulation of electrons and protons observed by the CALorimetric Electron Telescope onboard the International Space Station for about 7 years since October 2015, during the transition phase from the descending phase of the 24th solar cycle to the ascending phase of the 25th solar cycle. The observed variations of electron and proton count rates at an identical average rigidity of 3.8 GV show a clear charge-sign dependence of the solar modulation of galactic cosmic rays (GCRs), which is consistent with the prediction of a numerical drift model of the GCR transport in the heliosphere. It is also found that the ratio of 3.8 GV proton count rate to the neutron monitor count rate in the ascending phase of solar cycle 25 is clearly different from that in the descending phase of cycle 24. Correlations between the electron (proton) count rate and the heliospheric environmental parameters, such as the current sheet tilt angle, are a useful tool in further developing a numerical model of solar modulation. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Cosmology

Generative AI in Health Economics and Outcomes Research: A Taxonomy of Key Definitions and Emerging Applications – an ISPOR Working Group Report

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fleurence, Rachael L. Wang, Xiaoyan Bian, Jiang Higashi, Mitchell K. Ayer, Turgay Xu, Hua Dawoud, Dalia Chhatwal, Jagpreet Office of the Director National Institutes of Health National Institute of Biomedical Imaging and Bioengineering BethesdaMD United States Tulane University School of Public Health and Tropical Medicine New OrleansLA United States Intelligent Medical Objects RosemontIL United States College of Medicine University of Florida FL United States Biomedical Informatics Clinical and Translational Science Institute University of Florida FL United States Office of Data Science and Research Implementation University of Florida Health GainesvilleFL United States ISPOR The Professional Society for Health Economics and Outcomes Research LawrencevilleNJ United States Center for Health & Humanitarian Systems Georgia Institute of Technology AtlantaGA United States Value Analytics Labs BostonMA United States Institute Department of Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States National Institute for Health and Care Excellence London United Kingdom Cairo University Faculty of Pharmacy Cairo Egypt Institute for Technology Assessment Massachusetts General Hospital Harvard Medical School BostonMA United States Center for Health Decision Science Harvard University BostonMA United States

Objective: This article offers a taxonomy of generative artificial intelligence (AI) for health economics and outcomes research (HEOR), explores its emerging applications, and outlines methods to enhance the accuracy and reliability of AI-generated outputs. Methods: The review defines foundational generative AI concepts and highlights current HEOR applications, including systematic literature reviews, health economic modeling, real-world evidence generation, and dossier development. Approaches such as prompt engineering (zero-shot, few-shot, chain-of-thought, persona pattern prompting), retrieval-augmented generation, model fine-tuning, and the use of domain-specific models are introduced to improve AI accuracy and reliability. Results: Generative AI shows significant potential in HEOR, enhancing efficiency, productivity, and offering novel solutions to complex challenges. Foundation models are promising in automating complex tasks, though challenges remain in scientific reliability, bias, interpretability, and workflow integration. The article discusses strategies to improve the accuracy of these AI tools. Conclusion: Generative AI could transform HEOR by increasing efficiency and accuracy across various applications. However, its full potential can only be realized by building HEOR expertise and addressing the limitations of current AI technologies. As AI evolves, ongoing research and innovation will shape its future role in the field. © 2024, CC BY.

关键词： Generative adversarial networks

The ELEVATE-AI LLMs Framework: An Evaluation Framework for Use of Large Language Models in HEOR: An ISPOR Working Group Report

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fleurence, Rachael L. Dawoud, Dalia Bian, Jiang Higashi, Mitchell K. Wang, Xiaoyan Xu, Hua Chhatwal, Jagpreet Ayer, Turgay Office of the Director National Institutes of Health National Institute of Biomedical Imaging and Bioengineering BethesdaMD United States National Institute for Health and Care Excellence London United Kingdom Cairo University Faculty of Pharmacy Cairo Egypt Health Outcomes and Biomedical Informatics College of Medicine University of Florida FL United States Biomedical Informatics Clinical and Translational Science Institute University of Florida FL United States Office of Data Science and Research Implementation University of Florida Health GainesvilleFL United States ISPOR The Professional Society for Health Economics and Outcomes Research LawrencevilleNJ United States Tulane University School of Public Health and Tropical Medicine New OrleansLA United States Intelligent Medical Objects RosemontIL United States Institute Department of Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States Institute for Technology Assessment Massachusetts General Hospital Harvard Medical School BostonMA United States Center for Health Decision Science Harvard University BostonMA United States Value Analytics Labs BostonMA United States Center for Health & Humanitarian Systems Georgia Institute of Technology AtlantaGA United States

Introduction: Generative Artificial Intelligence, particularly large language models (LLMs), offers transformative potential for Health Economics and Outcomes Research (HEOR). However, evaluating the quality, transparency, and rigor of LLM-assisted research lacks standardized guidance. This article introduces the ELEVATE-AI LLMs framework and checklist, designed to support researchers and reviewers in assessing LLM use in HEOR. Methods: The ELEVATE-AI LLMs framework was developed through a targeted review of existing guidelines and evaluation frameworks. The framework comprises ten evaluation domains, including model characteristics, accuracy, comprehensiveness, and fairness. The accompanying checklist operationalizes the framework. To validate the framework, we applied it to two published studies, demonstrating its usability across different HEOR tasks. Results: The ELEVATE-AI LLMs framework provides a comprehensive structure for evaluating LLM-assisted research, while the checklist facilitates practical application. Validation of the framework and checklist on studies of systematic literature reviews and health economic modeling highlighted their ability to identify strengths and gaps in reporting. Limitations: While the ELEVATE-AI LLMs framework provides robust guidance, its broader generalizability and applicability to diverse HEOR tasks require further empirical testing. Additionally, several metrics adapted from computer science, need further validation in HEOR contexts. Conclusion: The ELEVATE-AI LLMs framework and checklist fill a critical gap in HEOR by offering structured guidance for evaluating LLM-assisted research. By promoting transparency, accuracy, and reproducibility, they aim to standardize and improve the integration of LLMs into HEOR, ensuring their outputs meet the field's rigorous standards. © 2024, CC BY.

关键词： Ability testing

Continuous-time fitted value iteration for robust policies

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Lutter, Michael Belousov, Boris Mannor, Shie Fox, Dieter Garg, Animesh Peters, Jan Intelligent Autonomous Systems group Computer Science Department Technical University of Darmstadt Darmstadt Germany Andrew and Erna Viterbi Faculty of Electrical & Computer Engineering Technion – Israel Institute of Technology and a Distinguished Scientist at NVIDIA Tel Aviv Israel Allen School of Computer Science & Engineering University of Washington and Senior Director of Robotics Research NVIDIA Washington Seattle United States Computer Science Department University of Toronto NVIDIA Toronto Canada

Solving the Hamilton-Jacobi-Bellman equation is important in many domains including control, robotics and economics. Especially for continuous control, solving this differential equation and its extension the Hamilton-Jacobi-Isaacs equation, is important as it yields the optimal policy that achieves the maximum reward on a give task. In the case of the Hamilton-Jacobi-Isaacs equation, which includes an adversary controlling the environment and minimizing the reward, the obtained policy is also robust to perturbations of the dynamics. In this paper we propose continuous fitted value iteration (cFVI) and robust fitted value iteration (rFVI). These algorithms leverage the non-linear control-affine dynamics and separable state and action reward of many continuous control problems to derive the optimal policy and optimal adversary in closed form. This analytic expression simplifies the differential equations and enables us to solve for the optimal value function using value iteration for continuous actions and states as well as the adversarial case. Notably, the resulting algorithms do not require discretization of states or actions. We apply the resulting algorithms to the Furuta pendulum and cartpole. We show that both algorithms obtain the optimal policy. The robustness Sim2Real experiments on the physical systems show that the policies successfully achieve the task in the real-world. When changing the masses of the pendulum, we observe that robust value iteration is more robust compared to deep reinforcement learning algorithm and the non-robust version of the algorithm. Videos of the experiments are shown at https://***/view/rfvi Copyright © 2021, The Authors. All rights reserved.

关键词： Dynamic programming

How Android Developers Handle Evolution-induced API Compatibility Issues: A Large-scale Study

学校读者我要写书评

暂无评论

How Android Developers Handle Evolution-induced API Compatib...

International Conference on Software engineering (ICSE)

作者： Hao Xia Yuan Zhang Yingtian Zhou Xiaoting Chen Yang Wang Xiangyu Zhang Shuaishuai Cui Geng Hong Xiaohan Zhang Min Yang Zhemin Yang Fudan University Purdue University Ministry of Education Shanghai Institute of Intelligent Electronics & Systems Shanghai Institute for Advanced Communication and Data Science and Engineering Research Center of CyberSecurity Auditing and Monitoring China

ISBN: (数字)9781450371216

ISBN: (纸本)9781728165196

As Android platform evolves in a fast pace, API-related compatibility issues become a significant challenge for developers. To handle an incompatible API invocation, developers mainly have two choices: merely performing sufficient checks to avoid invoking incompatible APIs on platforms that do not support them, or gracefully providing replacement implementations on those incompatible platforms. As providing more consistent app behaviors, the latter one is more recommended and more challenging to adopt. However, it is still unknown how these issues are handled in the real world, do developers meet difficulties and what can we do to help them. In light of this, this paper performs the first large-scale study on the current practice of handling evolution-induced API compatibility issues in about 300,000 Android market apps, and more importantly, their solutions (if exist). Actually, it is in general very challenging to determine if developers have put in countermeasure for a compatibility issue, as different APIs have diverse behaviors, rendering various repair. To facilitate a large-scale study, this paper proposes RAPID, an automated tool to determine whether a compatibility issue has been addressed or not, by incorporating both static analysis and machine learning techniques. Results show that our trained classifier is quite effective by achieving a F1-score of 95.21% and 91.96% in the training stage and the validation stage respectively. With the help of RAPID, our study yields many interesting findings, e.g. developers are not willing to provide alternative implementations when handling incompatible API invocations (only 38.4%); for those incompatible APIs that Google gives replacement recommendations, the ratio of providing alternative implementations is significantly higher than those without recommendations; developers find more ways to repair compatibility issues than Google's recommendations and the knowledge acquired from these experienced developers would b

关键词： Training Static analysis Maintenance engineering Tools Rendering (computer graphics) Internet Software engineering

A Predictive-Trend-Aware and Critical-Path-Estimation-Based Method for Workflow Scheduling Upon Cloud Services

学校读者我要写书评

暂无评论

A Predictive-Trend-Aware and Critical-Path-Estimation-Based ...

IEEE International Conference on Services Computing (SCC)

作者： Yi Pan Xiaoning Sun Yunni Xia Wanbo Zheng Xin Luo College of Computer Science Chongqing University Chongqing China Data Science Research Center Faculty of Science Kunming University of Science and Technology Kunming China Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China Hengrui (Chongqing) Artificial Intelligence Research Center Cloudwalk China

ISBN: (数字)9781728187891

ISBN: (纸本)9781728187907

The cloud computing paradigm is featured by its ability to offer elastic computational resource provisioning patterns and deliver on-demand and versatile services. It's thus getting increasingly popular to build business process and workflow-based applications upon cloud computing platforms. However, it remains a difficulty to guarantee cost-effectiveness and quality of service of cloud-based workflows because real-world cloud services are usually subject to real-time performance variations or fluctuations. Existing researches mainly consider that cloud are with constant performance and formulate the scheduling decision-making as a static optimization problem. In this work, instead, we consider that scientific computing processes to be supported by decentralized cloud infrastructures are with fluctuating QoS and aim at managing the monetary cost of workflows with the completion-time constraint to be satisfied. We address the performance-trend-aware workflow scheduling problem by leveraging a time-series-based prediction model and a Critical-Path-Duration-Estimation-based (CPDE for short) scheduling strategy. The proposed method is capable of exploiting real-time trends of performance changes of cloud infrastructures and generating dynamic workflow scheduling plans. To prove the effectiveness of our proposed method, we build a large-prime-number-generation workflow supported by real-world third-party commercial clouds and show that our method clearly beats existing approaches in terms of cost, workflow completion time, and Service-Level-Agreement (SLA) violation rate.

关键词： Cloud computing Processor scheduling Computational modeling Quality of service Predictive models Dynamic scheduling Real-time systems

Exploratory study of highly susceptible to SARS-CoV-2 populations

学校读者我要写书评

暂无评论

Life Research 2022年第3期5卷 10-14页

作者： Xiaodong Jia Chengliang Yin Shanshan Lu Yan Chen Qingyan Liu Junfan Bai Lei Zhi Yinying Lu Comprehensive Liver Cancer Center The Fifth Medical Center of PLA General HospitalBeijingChina.0000-0001-8262-5749 National Engineering Laboratory for Medical Big Data Application Technology Chinese PLA General HospitalBeijingChina Faculty of Medicine Macao University of Science and TechnologyMacaoChina Medical Big Data Research Center Medical Innovation Research Division of PLA General HospitalBeijingChina Center for Synthetic and Systems Biology(CSSB) Tsinghua UniversityBeijingChina Peking University BeijingChina Department of Chronic Disease Luzhou Center for Disease Control and PreventionLuzhouChina

The coronavirus disease 2019(COVID-19),caused by severe acute respiratory syndrome coronavirus 2(SARS-CoV-2),is threatening public *** human angiotensin-converting enzyme 2(ACE2)has a remarkably high affinity binding to *** study explored whether certain populations,including obese and cancer patients,are susceptible to *** expression pattern of ACE2 in normal and tumor tissues of cancer patients was compared by the search for network database and re-analysis of pubic *** level of ACE2 expression in normal adipose tissue was higher than that in normal lung tissue,which indicated the adipose tissue might be vulnerable to SARS-CoV-2;the levels of ACE2 expressed by adipocytes and adipose progenitor cells were similar between non-obese individuals and obese individuals(BMI>29),but obese individuals have more adiposes so as to increase the number of ACE2-expressing cells;the expression of ACE2 in tumor tissues posed by five different types of cancers increased significantly compared with that in adjacent ***,we proposed the following hypothesis:the obese individuals and five types of cancer patients might have a higher risk of SARS-CoV-2 infection,which might become the target population of SARS-CoV-2 infection in the future.

关键词： COVID-19 adipose tissue obesity cancer ACE2

Smart online charging algorithm for electric vehicles via customized actor-critic learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Yongsheng Wang, Hao Li, Demin Zhang, Guanglin College of Information Science and Technology Donghua University Engineering Research Center of Digitized Textile and Apparel Technology Ministry of Education Shanghai201620 China The Department of Data Science and Artificial Intelligence Faculty of Information Technology Monash University MelbourneVIC3800 Australia The Stanford Sustainable Systems Lab Stanford University StanfordCA94305 United States

With the advances in the Internet of Things technology, electric vehicles (EVs) have become easier to schedule in daily life, which is reshaping the electric load curve. It is important to design efficient charging algorithms to mitigate the negative impact of EV charging on the power grid. This paper investigates an EV charging scheduling problem to reduce the charging cost while shaving the peak charging load, under unknown future information about EVs, such as arrival time, departure time, and charging demand. First, we formulate an EV charging problem to minimize the electricity bill of the EV fleet and study the EV charging problem in an online setting without knowing future information. We develop an actor-critic learning-based smart charging algorithm (SCA) to schedule the EV charging against the uncertainties in EV charging behaviors. The SCA learns an optimal EV charging strategy with continuous charging actions instead of discrete approximation of charging. We further develop a more computationally efficient customized actor-critic learning charging algorithm (CALC) by reducing the state dimension and thus improving the computational efficiency. Finally, simulation results show that our proposed SCA can reduce EVs' expected cost by 24.03%, 21.49%, 13.80%, compared with the Eagerly Charging Algorithm, Online Charging Algorithm, RL-based Adaptive Energy Management Algorithm, respectively. CALC is more computationally efficient, and its performance is close to that of SCA with only a gap of 5.56% in the cost. Copyright © 2021, The Authors. All rights reserved.

关键词： Computational efficiency