检索结果-内蒙古大学图书馆

Equivariant spatio-temporal attentive graph networks to simulate physical dynamics 23

学校读者我要写书评

暂无评论

Equivariant spatio-temporal attentive graph networks to simu...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Liming Wu Zhichao Hou Jirui Yuan Yu Rong Wenbing Huang Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Department of Computer Science North Carolina State University Institute for AI Industry Research (AIR) Tsinghua University Tencent AI Lab

Learning to represent and simulate the dynamics of physical systems is a crucial yet challenging task. Existing equivariant Graph Neural Network (GNN) based methods have encapsulated the symmetry of physics, e.g., translations, rotations, etc, leading to better generalization ability. Nevertheless, their frame-to-frame formulation of the task overlooks the non-Markov property mainly incurred by unobserved dynamics in the environment. In this paper, we reformulate dynamics simulation as a spatio-temporal prediction task, by employing the trajectory in the past period to recover the Non-Markovian interactions. We propose Equivariant Spatio-Temporal Attentive Graph Networks (ESTAG), an equivariant version of spatio-temporal GNNs, to fulfill our purpose. At its core, we design a novel Equivariant Discrete Fourier Transform (EDFT) to extract periodic patterns from the history frames, and then construct an Equivariant Spatial Module (ESM) to accomplish spatial message passing, and an Equivariant Temporal Module (ETM) with the forward attention and equivariant pooling mechanisms to aggregate temporal message. We evaluate our model on three real datasets corresponding to the molecular-, protein- and macro-level. Experimental results verify the effectiveness of ESTAG compared to typical spatio-temporal GNNs and equivariant GNNs.

关键词：

Identification of Inhomogeneities According to Potential Field Data Using the Near-Boundary Element Method 16

学校读者我要写书评

暂无评论

Identification of Inhomogeneities According to Potential Fie...

16th IEEE International Conference on computer science and Information Technologies, CSIT 2021

作者： Zhuravchak, Liubov Zabrodska, Nataliya National University Lviv Polytechnic Software Department of Institute of Computer Science and Information Technologies Bandera street 12 Lviv Ukraine Branch of S.I Subbotin Institute of Geophysics National Academy of Sciences Department of Geoelectromagnetic Methods of Carpathian Naukova street 3-b Lviv Ukraine

ISBN: (纸本)9781665442572

The step-by-step algorithm for the approximate recognition of inclusions in the object according to potential field data is given. It is based on the repeated solution of a direct problem by high-precision methods of boundary, near-boundary and partly boundary elements. On the example of the use of electrical profiling method data, regularities between the distribution of apparent resistivity at the half-plane boundary and the parameters of inclusions are derived. © 2021 IEEE.

关键词： Boundary element method

Intensionalizing Abstract Meaning Representations: Non-Veridicality and Scope 15

学校读者我要写书评

暂无评论

Intensionalizing Abstract Meaning Representations: Non-Verid...

Joint 15th Linguistic Annotation Workshop and 3rd Designing Meaning Representations Workshop, LAW-DMR 2021

作者： Williamson, Gregor Elliott, Patrick Ji, Yuxin Department of Computer Science Emory University AtlantaGA30322 United States Department of Linguistics and Philosophy Massachusetts Institute of Technology CambridgeMA02139 United States Department of Quantitative Theory and Methods Emory University AtlantaGA30322 United States

ISBN: (纸本)9781954085855

Meaning Representation (AMR) is a graphical meaning representation language designed to represent propositional information about argument structure. However, at present it is unable to satisfyingly represent non-veridical intensional contexts, often licensing inappropriate inferences. In this paper, we show how to resolve the problem of non-veridicality without appealing to layered graphs through a mapping from AMRs into Simply-Typed Lambda Calculus (STLC). At least for some cases, this requires the introduction of a new role:content which functions as an intensional operator. The translation proposed is inspired by the formal linguistics literature on the event semantics of attitude reports. Next, we address the interaction of quantifier scope and intensional operators in so-called de re/de dicto ambiguities. We adopt a scope node from the literature and provide an explicit multidimensional semantics utilizing Cooper storage which allows us to derive the de re and de dicto scope readings as well as intermediate scope readings which prove difficult for accounts without a scope node. © 2021 Association for Computational Linguistics.

关键词： Semantics

Closing the Performance Gap with Modern C++

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Heller, Thomas Kaiser, Hartmut Diehl, Patrick Fey, Dietmar Schweitzer, Marc Alexander Computer Science 3 Computer Architectures Friedrich-Alexander-University Germany Center for Computation and Technology Louisiana State University United States Institute for Numerical Simulation University of Bonn Germany Meshfree Multiscale Methods Fraunhofer SCAI Schloss Birlinghoven Germany The STEllAR Group United States

On the way to Exascale, programmers face the increasing challenge of having to support multiple hardware architectures from the same code base. At the same time, portability of code and performance are increasingly difficult to achieve as hardware architectures are becoming more and more diverse. Today's heterogeneous systems often include two or more completely distinct and incompatible hardware execution models, such as GPGPU's, SIMD vector units, and general purpose cores which conventionally have to be programmed using separate tool chains representing non-overlapping programming models. The recent revival of interest in the industry and the wider community for the C++ language has spurred a remarkable amount of standardization proposals and technical specifications in the arena of concurrency and parallelism. This recently includes an increasing amount of discussion around the need for a uniform, higher-level abstraction and programming model for parallelism in the C++ standard targeting heterogeneous and distributed computing. Such an abstraction should perfectly blend with existing, already standardized language and library features, but should also be generic enough to support future hardware developments. In this paper, we present the results from developing such a higher-level programming abstraction for parallelism in C++ which aims at enabling code and performance portability over a wide range of architectures and for various types of parallelism. We present and compare performance data obtained from running the well-known STREAM benchmark ported to our higher level C++ abstraction with the corresponding results from running it natively. We show that our abstractions enable performance at least as good as the comparable base-line benchmarks while providing a uniform programming API on all compared target architectures. Copyright © 2022, The Authors. All rights reserved.

关键词： C++ (programming language)

Robust Graph Matching Using An Unbalanced Hierarchical Optimal Transport Framework

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Cheng, Haoran Luo, Dixin Xu, Hongteng School of Computer Science and Technology Beijing Institute of Technology Beijing100081 China Key Laboratory of Artificial Intelligence Ministry of Education China Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods China

Graph matching is one of the most significant graph analytic tasks, which aims to find the node correspondence across different graphs. Most existing graph matching approaches mainly rely on topological information, whose performances are often sub-optimal and sensitive to data noise because of not fully leveraging the multi-modal information hidden in graphs, such as node attributes, subgraph structures, etc. In this study, we propose a novel and robust graph matching method based on an unbalanced hierarchical optimal transport (UHOT) framework, which, to our knowledge, makes the first attempt to exploit cross-modal alignment in graph matching. In principle, applying multilayer message passing, we represent each graph as layer-wise node embeddings corresponding to different modalities. Given two graphs, we align their node embeddings within the same modality and across different modalities, respectively. Then, we infer the node correspondence by the weighted average of all the alignment results. This method is implemented as computing the UHOT distance between the two graphs — each alignment is achieved by a node-level optimal transport plan between two sets of node embeddings, and the weights of all alignment results correspond to an unbalanced modality-level optimal transport plan. Experiments on various graph matching tasks demonstrate the superiority and robustness of our method compared to state-of-the-art approaches. Our implementation is available at https://***/Dixin-Lab/UHOT-GM. © 2023, CC BY.

关键词： Graph embeddings

On a Cyclometric Modification of the Chua System

学校读者我要写书评

暂无评论

On a Cyclometric Modification of the Chua System

International IEEE Conference and Workshop: Óbuda on Electrical and Power Engineering (CANDO-EPE)

作者： Bálint Nagy Antal Joós Attila Kovari Department of Mathematics Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Natural Sciences Kandó Kálmán Faculty of Electrical Engineering Institute of Electrophysics Obuda University Budapest Hungary Department of Applied Quantitative Methods Faculty of Finance and Accountancy Budapest Business University Budapest Hungary Kandó Kálmán Faculty of Electrical Engineering Institute of Electronics and Communication Systems Obuda University Budapest Hungary Faculty of Computer Science Institute of Digital Technology Eszterházy Károly Catholic University Eger Hungary Department of Natural Sciences Institute of Engineering University of Dunaújváros Dunaujvaros Hungary GAMF Faculty of Engineering and Computer Science John Von Neumann University Kecskemét Hungary

Chaos is not only a unique chapter in the theory of dynamical systems but also a useful one with many applications in the field of communications. In this work a cyclometric modification of the well-known example of chaotic systems, the modified differential equations describing the behavior of the Chua-circuit is investigated. The results obtained can be applied in the encryption methods of the implementation of different communication channels like machine-machine or cognitive one.

关键词：

Enhancement of heat transfer through alloys and nanoparticle over a melted sheet: A Koo and Kleinstreuer (K-K) model

学校读者我要写书评

暂无评论

Partial Differential Equations in Applied Mathematics 2024年 11卷

作者： Kumar, K. Ganesh Praveena, M.M. Vishwanath, S. Vidhyarani, N.J. Mahesh Prakasha, D.G. Khan, M. Ijaz Sadikova, Albina Waqas, M. Department of Mathematics Nitte (Deemed to be University) N. M. A. M. Institute of Technology Nitte Department of Mathematics Ramaiah Institute of Technology Department of Mathematics Sri Sairam College of Engineering Anekal Department of Mathematics University BDT College of Institute Department of Mathematics Davangere University Department of Mechanical Engineering Prince Mohammad Bin Fahd University Department of Mathematics and Its Teaching Methods in Primary Education Tashkent State Pedagogical University Department of Computer Science National University of Technology Department of Computer Science and Mathematics Lebanese American University

Alloys are used in a wide variety of contexts, including aircraft building, the military, industry, medicine, and manufacturing. Alloys including tools, equipment, cars, and structures. Furniture, shipping containers, and medical supply storage containers are among products that benefit from the usage of aluminium alloys. To further enhance simultaneous heat transmission, scientists have developed nano-fluids, which are essentially nano-particle suspensions in a regular fluid. Ferric Sulfate may be added to soil to improve its quality and is also used to clean water. Iron (3+) sulphate is an iron (III) and sulfate (III) combination with a 3:2 ratio of iron (III) to sulfate (III) ions. As a catalyst, mordant, and astringent, it serves several purposes. It is a sulphate of a metal and a molecule of iron. Due of these purposes, we employ the K-K model to study how alloys and nanoparticles affect surface flow and heat transfer. By making use of the boundary layer approach and the flow assumptions, the partial differential equations (PDEs) were generated by approximating the Navier-Stokes equation. This system is transformed into ordinary differential equations (ODE's) using similarity transformations. Using the BVP4C method, a system with non-dimensions is defined. Mathematical and pictorial explanations are provided for the consequences of the key physical variables. It is founded that the magnitude of the temperature field is directly proportional to the R value;a higher value indicates more heat conduction to the liquid. Additionally, the velocity of the fluid lessened by the impact of melting effect. © 2024 The Author(s)

关键词： Darcy Forchheimer medium Ferric sulfate nanoparticles Koo and Kleinstreuer Melting sheet Nimonic 80A alloys Radiative heat transfer

INFORMED BAYESIAN SURVIVAL ANALYSIS

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bartoš, František Aust, Frederik Haaf, Julia M. Department of Psychological Methods University of Amsterdam Noord-Holland Netherlands Institute of Computer Science Czech Academy of Sciences Prague Czech Republic

Background: We provide an overview of Bayesian estimation, hypothesis testing, and model-averaging and illustrate how they benefit parametric survival analysis. We contrast the Bayesian framework to the currently dominant frequentist approach and highlight advantages, such as seamless incorporation of historical data, continuous monitoring of evidence, and incorporating uncertainty about the true data generating process. methods: We illustrate the application of the outlined Bayesian approaches on an example data set from a colon cancer trial. We assess the performance of Bayesian parametric survival analysis and maximum likelihood survival models with AIC/BIC model selection in fixed-n and sequential designs with a simulation study. Results: In the example data set, the Bayesian framework provided evidence for the absence of a positive treatment effect of adding Cetuximab to FOLFOX6 regimen on disease-free survival in patients with resected stage III colon cancer. Furthermore, the Bayesian sequential analysis would have terminated the trial 10.3 months earlier than the standard frequentist analysis. In a simulation study with sequential designs, the Bayesian framework on average reached a decision in almost half the time required by the frequentist counterparts, while maintaining the same power, and an appropriate false-positive rate. Under model misspecification, the Bayesian framework resulted in higher false-negative rate compared to the frequentist counterparts, which resulted in a higher proportion of undecided trials. In fixed-n designs, the Bayesian framework showed slightly higher power, slightly elevated error rates, and lower bias and RMSE when estimating treatment effects in small samples. We found no noticeable differences for survival predictions. We have made the analytic approach readily available to other researchers in the RoBSA R package. Conclusions: The outlined Bayesian framework provides several benefits when applied to parametric survival ana

关键词： Bayesian networks

BAYESDIFF: ESTIMATING PIXEL-WISE UNCERTAINTY IN DIFFUSION VIA BAYESIAN INFERENCE

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Kou, Siqi Gan, Lei Wang, Dequan Li, Chongxuan Deng, Zhijie Qing Yuan Research Institute SEIEE Shanghai Jiao Tong University China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China School of Computer Science Fudan University China Shanghai Artificial Intelligence Laboratory China

Diffusion models have impressive image generation capability, but low-quality generations still exist, and their identification remains challenging due to the lack of a proper sample-wise metric. To address this, we propose BayesDiff, a pixel-wise uncertainty estimator for generations from diffusion models based on Bayesian inference. In particular, we derive a novel uncertainty iteration principle to characterize the uncertainty dynamics in diffusion, and leverage the last-layer Laplace approximation for efficient Bayesian inference. The estimated pixel-wise uncertainty can not only be aggregated into a sample-wise metric to filter out low-fidelity images but also aids in augmenting successful generations and rectifying artifacts in failed generations in text-to-image tasks. Extensive experiments demonstrate the efficacy of BayesDiff and its promise for practical applications. Our code is available at https://***/karrykkk/BayesDiff. Copyright © 2023, The Authors. All rights reserved.

关键词： Pixels