检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pirnay, Jonathan Rittig, Jan G. Wolf, Alexander B. Grohe, Martin Burger, Jakob Mitsos, Alexander Grimm, Dominik G. Technical University of Munich TUM Campus Straubing for Biotechnology and Sustainability Bioinformatics Straubing Germany University of Applied Sciences Weihenstephan-Triesdorf Bioinformatics Straubing Germany Process Systems Engineering AVT.SVT RWTH Aachen University Aachen Germany Technical University of Munich TUM Campus Straubing for Biotechnology and Sustainability Laboratory of Chemical Process Engineering Straubing Germany Chair of Computer Science 7 RWTH Aachen University Aachen Germany Aachen Germany Forschungszentrum Jülich GmbH Institute of Climate and Energy Systems ICE-1: Energy Systems Engineering Jülich Germany

Generative deep learning has become pivotal in molecular design for drug discovery and materials science. A widely used paradigm is to pretrain neural networks on string representations of molecules and fine-tune them using reinforcement learning on specific objectives. However, string-based models face challenges in ensuring chemical validity and enforcing structural constraints like the presence of specific substructures. We propose to instead combine graph-based molecular representations, which can naturally ensure chemical validity, with transformer architectures, which are highly expressive and capable of modeling long-range dependencies between atoms. Our approach iteratively modifies a molecular graph by adding atoms and bonds, which ensures chemical validity and facilitates the incorporation of structural constraints. We present GraphXForm, a decoder-only graph transformer architecture, which is pretrained on existing compounds and then fine-tuned using a new training algorithm that combines elements of the deep cross-entropy method with self-improvement learning from language modeling, allowing stable fine-tuning of deep transformers with many layers. We evaluate GraphXForm on two solvent design tasks for liquid-liquid extraction, showing that it outperforms four state-of-the-art molecular design techniques, while it can flexibly enforce structural constraints or initiate the design from existing molecular structures. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Structure aware negative sampling in knowledge graphs

arXiv

引用

arXiv 2020年

作者： Ahrabian, Kian Feizi, Aarash Salehi, Yasmin Hamilton, William L. Bose, Avishek Joey School of Computer Science McGill University Canada Department of Electrical and Computer Engineering McGill University Canada Montreal Institute of Learning Algorithms Mila Canada Canada CIFAR AI Chair Canada

Learning low-dimensional representations for entities and relations in knowledge graphs using contrastive estimation represents a scalable and effective method for inferring connectivity patterns. A crucial aspect of contrastive learning approaches is the choice of corruption distribution that generates hard negative samples, which force the embedding model to learn discriminative representations and find critical characteristics of observed data. While earlier methods either employ too simple corruption distributions, i.e. uniform, yielding easy uninformative negatives or sophisticated adversarial distributions with challenging optimization schemes, they do not explicitly incorporate known graph structure resulting in suboptimal negatives. In this paper, we propose Structure Aware Negative Sampling (SANS), an inexpensive negative sampling strategy that utilizes the rich graph structure by selecting negative samples from a node’s k-hop neighborhood. Empirically, we demonstrate that SANS finds high-quality negatives that are highly competitive with SOTA methods, and requires no additional parameters nor difficult adversarial optimization. Copyright © 2020, The Authors. All rights reserved.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

A Survey on Indoor Visible Light Positioning Systems: Fundamentals, Applications, and Challenges

arXiv

引用

arXiv 2024年

作者： Zhu, Zhiyu Yang, Yang Chen, Mingzhe Guo, Caili Cheng, Julian Cui, Shuguang The Beijing Key Laboratory of Network System Architecture and Convergence School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral GablesFL33146 United States The Beijing Laboratory of Advanced Information Networks School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The Faculty of Applied Science School of Engineering The University of British Columbia KelownaBCV1V 1V7 Canada The Chinese University of Hong Kong Shenzhen518172 China

The growing demand for location-based services in areas like virtual reality, robot control, and navigation has intensified the focus on indoor localization. Visible light positioning (VLP), leveraging visible light communications (VLC), becomes a promising indoor positioning technology due to its high accuracy and low cost. This paper provides a comprehensive survey of VLP systems. In particular, since VLC lays the foundation for VLP, we first present a detailed overview of the principles of VLC. Then, we provide an in-depth overview of VLP algorithms. The performance of each positioning algorithm is also compared in terms of various metrics such as accuracy, coverage, and orientation limitation. Beyond the physical layer studies, the network design for a VLP system is also investigated, including multi-access technologies, resource allocation, and light-emitting diode (LED) placements. Next, the applications of the VLP systems are overviewed. Finally, this paper outlines open issues, challenges, and opportunities for the research field. In a nutshell, this paper constitutes the first holistic survey on VLP from state-of-the-art studies to practical uses. Copyright © 2024, The Authors. All rights reserved.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Scheduling for Delay-Critical Packets in a Networked Control System Using WirelessHART

Dynamic Scheduling for Delay-Critical Packets in a Networked...

引用

IEEE International Conference on Communications (ICC)

作者： Samuele Zoppi Jaya Prakash Champati James Gross Wolfgang Kellerer Chair of Communication Networks Technical University of Munich Germany School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden

ISBN: (数字)9781728150895

ISBN: (纸本)9781728150901

In future industrial scenarios, Wireless Sensor Networks (WSN) are envisioned to support the traffic of Networked Control Systems (NCS). WirelessHART is a prevalent WSN protocol that uses the Time Slotted Channel Hopping (TSCH) medium access to cope with the delay and reliability requirements of NCS in the harsh industrial environment. In TSCH, time slots and frequencies can be scheduled by a network coordinator to provide Quality of Service (QoS). In contrast to previous works that consider the end-to-end delay requirement of a flow of packets, we focus on a finite sequence of time-critical packets. These packets may belong to a time-critical message whose latency could significantly impact the NCS. Given an end-to-end delay deadline, our objective is to minimize the Delay Violation Probability (DVP) for a finite sequence of packets by dynamically scheduling the time slots in each frame. This is a challenging task as DVP depends on the instantaneous state of the network and requires its transient analysis. In this work, we model the wireless NCS as a two-queue lossy wireless network and propose the first transient analysis of DVP for a finite sequence of time-critical packets. Noting that DVP cannot be directly used for dynamic resource allocation, we propose a heuristic algorithm by relating DVP with the network's throughput. The proposed heuristic maximizes the expected throughput, is computed by solving a finite-horizon Markov Decision Process (MDP), and can be implemented at the network coordinator. Using simulation we demonstrate that the MDP-based heuristic achieves lower DVP compared to the classical MaxWeight and Weighted-Fair Queuing.

关键词： Delays Wireless sensor networks Reliability Dynamic scheduling Time factors Time division multiple access Quality of service

来源：评论

学校读者我要写书评

暂无评论

A Highly Efficient Dynamical Core of Atmospheric General Circulation Model based on Leap-Format

A Highly Efficient Dynamical Core of Atmospheric General Cir...

引用

International Symposium on Parallel and Distributed Processing (IPDPS)

作者： Hang Cao Liang Yuan He Zhang Baodong Wu Shigang Li Pengqi Lu Yunquan Zhang Yongjun Xu Minghua Zhang State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Institute of Atmospheric Physics Chinese Academy of Sciences Department of Computer Science ETH Zurich Institute of Computing Technology Chinese Academy of Sciences

ISBN: (数字)9781728168760

ISBN: (纸本)9781728168777

The finite-difference dynamical core based on the equal-interval latitude-longitude mesh has been widely used for numerical simulations of the Atmospheric General Circulation Model (AGCM). Previous work utilizes different filtering schemes to alleviate the instability problem incurred by the unequal physical spacing at different latitudes, but they all incur high communication and computation overhead and become a scaling bottleneck. This paper proposes a new leap-format finite-difference computing scheme. It generalizes the usual finite-difference format with adaptive wider intervals and is able to maintain the computational stability in the grid updating. Therefore, the costly filtering scheme is eliminated. The new scheme is parallelized with a shifting communication method and implemented with fine communication optimizations based on a 3D decomposition. With the proposed leap-format computation scheme, the communication overhead of the AGCM is significantly reduced and good load balance is exhibited. The simulation results verify the correctness of the new leap-format scheme. The new scheme achieves the speed of 16.6 simulation-year-per-day (SYPD) and up to 3.3x speedup over the latest implementation.

关键词： Atmospheric modeling Computational modeling Mathematical model Three-dimensional displays Power system stability Stability analysis Two dimensional displays

来源：评论

学校读者我要写书评

暂无评论

GPU-based Parallel Heuristics for Capacited Vehicle Routing Problem

GPU-based Parallel Heuristics for Capacited Vehicle Routing ...

引用

IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT)

作者： Pramod Yelmewad Basavaraj Talawar Systems Parallelization & Architecture Research at NITK (SPARK) Department of Computer Science and Engineering National Institute of Technology Karnataka Mangalore India

ISBN: (数字)9781728168289

ISBN: (纸本)9781728168296

This paper presents the novel GPU-based parallel strategy for the heuristic algorithms to solve the large-scale Capacited Vehicle Routing Problem (CVRP). A combination of five improvement heuristic approaches has been used to improve the constructed feasible solution. It is noticed that a large amount of CPU time is spent in the solution improvement phase while improving a feasible solution. We aim to discover an independent part of the improvement heuristic approaches and make it run over the GPU platform simultaneously. The proposed parallel version has been tested on large-scale instances of up to 20000 customers. The parallel version offers speedup up to 176.12 × compared to the corresponding sequential version.

关键词： Heuristic algorithms Instruction sets Graphics processing units Data structures Vehicle routing Kernel Transportation

来源：评论

学校读者我要写书评

暂无评论

Extreme-Scale Ab initio Quantum Raman Spectra Simulations on the Leadership HPC System in China

Extreme-Scale Ab initio Quantum Raman Spectra Simulations on...

引用

Supercomputing Conference

作者： Honghui Shang Fang Li Yunquan Zhang Libo Zhang You Fu Yingxiang Gao Yangjun Wu Xiaohui Duan Rongfen Lin Xin Liu Ying Liu Dexun Chen SKL of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing China National Supercomputing Center in Wuxi China Shangdong University of Science and Technology Qingdao China Institute of Computing Technology Chinese Academy of Sciences Beijing China Tsinghua University Beijing China

ISBN: (数字)9781450384421

ISBN: (纸本)9781665483902

Raman spectroscopy provides chemical and compositional information that can serve as a structural fingerprint for various materials. Therefore, simulations of Raman spectra, including both quantum perturbation analyses and ground-state calculations, are of significant interest. However, highly accurate full quantum mechanical (QM) simulations of Raman spectra have previously been confined to small systems. For large systems such as biological materials, full QM simulations have an extremely high computational cost and remain challenging. In this work, robust new algorithms and advanced implementations on many-core architectures are employed to enable fast, accurate, and massively parallel full ab initio simulations of the Raman spectra of realistic biological systems containing up to 3006 atoms, with excellent strong and weak scaling. Up to a performance of 468.5 PFLOP / s in double-precision and 813.7 PLOPS/s in mixed-half precision is achieved on the new-generation Sunway high-performance computing system, suggesting the potential for new applications of the QM approach to biological systems.

关键词： Analytical models Leadership Quantum computing Computational modeling Biological system modeling High performance computing Perturbation methods

来源：评论

学校读者我要写书评

暂无评论

Unsupervised video decomposition using spatio-temporal iterative inference

arXiv

引用

arXiv 2020年

作者： Zablotskaia, Polina Dominici, Edoardo A. Sigal, Leonid Lehrmann, Andreas M. Department of Computer Science University of British Columbia Borealis AI VancouverBC Canada Vector Institute for AI CIFAR AI Chair

Unsupervised multi-object scene decomposition is a fast-emerging problem in representation learning. Despite significant progress in static scenes, such models are unable to leverage important dynamic cues present in video. We propose a novel spatio-temporal iterative inference framework that is powerful enough to jointly model complex multi-object representations and explicit temporal dependencies between latent variables across frames. This is achieved by leveraging 2D-LSTM, temporally conditioned inference and generation within the iterative amortized inference for posterior refinement. Our method improves the overall quality of decompositions, encodes information about the objects’ dynamics, and can be used to predict trajectories of each object separately. Additionally, we show that our model has a high accuracy even without color information. We demonstrate the decomposition, segmentation, and prediction capabilities of our model and show that it outperforms the state-of-the-art on several benchmark datasets, one of which was curated for this work and will be made publicly available. Copyright © 2020, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Structural Reinforcement in Mechanically Interlocked Two-Dimensional Polymers by Suppressing Interlayer Sliding

arXiv

引用

arXiv 2024年

作者： Yang, Ye Knapp, André Bodesheim, David Croy, Alexander Hambsch, Mike Naisa, Chandrasekhar Pohl, Darius Rellinghaus, Bernd Zhao, Changsheng Mannsfeld, Stefan C.B. Cuniberti, Gianaurelio Wang, Zhiyong Dong, Renhao Fery, Andreas Feng, Xinliang Center for Advancing Electronics Dresden Faculty of Chemistry and Food Chemistry Technische Universität Dresden Dresden Germany Institute of Physical Chemistry and Polymer Physics Leibniz Institute of Polymer Research Dresden Dresden Germany Institute for Materials Science Max Bergmann Center for Biomaterials TU Dresden Dresden Germany Institute of Physical Chemistry Friedrich Schiller University Jena Jena Germany Center for Advancing Electronics Dresden Faculty of Electrical and Computer Engineering Technische Universität Dresden Dresden Germany TUD Dresden University of Technology Dresden Germany College of Polymer Science and Engineering State Key Laboratory of Polymer Materials Engineering Sichuan University Chengdu China Germany Key Laboratory of Colloid and Interface Chemistry of the Ministry of Education School of Chemistry and Chemical Engineering Shandong University Jinan China TU Dresden Dresden Germany Chair for Physical Chemistry of Polymeric Materials Technical University Dresden Dresden Germany

Preserving the superior mechanical properties of monolayer two-dimensional (2D) materials when transitioning to bilayer and layer-stacked structures poses a great challenge, primarily arising from the weak van der Waals (vdW) forces that facilitate interlayer sliding and decoupling. Here, we discover that mechanically interlocked 2D polymers (2DPs) offer a means for structural reinforcement from monolayer to bilayer. Incorporating macrocyclic molecules with one and two cavities into 2DPs backbones enables the precision synthesis of mechanically interlocked monolayer (MI-M2DP) and bilayer (MI-B2DP). Intriguingly, we have observed an exceptionally high effective Young's modulus of 222.4±51.0 GPa for MI-B2DP, surpassing those of MI-M2DP (130.1±15.2 GPa), vdW-stacked MI-M2DPs (2×MI-M2DP, 8.1±0.9 GPa) and other reported multilayer 2DPs. Modeling studies demonstrate the extraordinary effectiveness of mechanically interlocked structures in minimizing interlayer sliding (~0.1 Å) and energy penalty (320 kcal/mol) in MI-B2DP compared to 2×MI-M2DP (~1.2 Å, 550 kcal/mol), thereby suppressing mechanical relaxation and resulting in prominent structural reinforcement. © 2024, CC BY-NC-ND.

关键词： Monolayers

来源：评论

学校读者我要写书评

暂无评论

I/O lower bounds for auto-tuning of convolutions in CNNs

arXiv

引用

arXiv 2020年

作者： Zhang, Xiaoyang Xiao, Junmin Tan, Guangming State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Science China

Convolution is the most time-consuming part in the computation of convolutional neural networks (CNNs), which have achieved great successes in numerous practical applications. Due to the complex data dependency and the increase in the amount of model samples, the convolution suffers from high overhead on data movement (i.e., memory access). This work provides comprehensive analysis and methodologies to minimize the communication for the convolution in CNNs. With an in-depth analysis of the recent I/O complexity theory under the red-blue game model, we develop a general I/O lower bound theory for a composite algorithm which consists of several different sub-computations. Based on the proposed theory, we establish the data movement lower bound results for two main convolution algorithms in CNNs, namely the direct convolution and Winograd algorithm, which represents the direct and indirect implementations of a convolution respectively. Next, derived from I/O lower bound results, we design the near I/O-optimal dataflow strategies for the two main convolution algorithms by fully exploiting the data reuse. Furthermore, in order to push the envelope of performance of the near I/O-optimal dataflow strategies further, an aggressive design of auto-tuning based on I/O lower bounds, is proposed to search an optimal parameter configuration for the direct convolution and Winograd algorithm on GPU, such as the number of threads and the size of shared memory used in each thread block. Finally, experiment evaluation results on the direct convolution and Winograd algorithm show that our dataflow strategies with the auto-tuning approach can achieve about 3.32× performance speedup on average over cuDNN. In addition, compared with TVM, which represents the state-of-the-art technique for auto-tuning, not only our auto-tuning method based on I/O lower bounds can find the optimal parameter configuration faster, but also our solution has higher performance than the optimal solution provided

关键词： Convolution

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：