检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Chen, Yuhong Song, Ailin Yin, Huifeng Zhong, Shuai Chen, Fuhai Xu, Qi Wang, Shiping Xu, Mingkun College of Computer and Data Science Fuzhou University Fuzhou China Guangdong Institute of Intelligence Science and Technology Hengqin Zhuhai China University of Electronic Science and Technology of China Chengdu China Center for Brain Inspired Computing Research Department of Precision Instrument Tsinghua University Beijing China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (纸本)157735897X

The rapid evolution of multimedia technology has revolutionized human perception, paving the way for multi-view learning. However, traditional multi-view learning approaches are tailored for scenarios with fixed data views, falling short of emulating the intricate cognitive procedures of the human brain processing signals sequentially. Our cerebral architecture seamlessly integrates sequential data through intricate feed-forward and feedback mechanisms. In stark contrast, traditional methods struggle to generalize effectively when confronted with data spanning diverse domains, highlighting the need for innovative strategies that can mimic the brain's adaptability and dynamic integration capabilities. In this paper, we propose a bio-neurologically inspired multiview incremental framework named MVIL aimed at emulating the brain's fine-grained fusion of sequentially arriving views. MVIL lies two fundamental modules: structured Hebbian plasticity and synaptic partition learning. The structured Hebbian plasticity reshapes the structure of weights to express the high correlation between view representations, facilitating a fine-grained fusion of view representations. Moreover, synaptic partition learning is efficient in alleviating drastic changes in weights and also retaining old knowledge by inhibiting partial synapses. These modules bionically play a central role in reinforcing crucial associations between newly acquired information and existing knowledge repositories, thereby enhancing the network's capacity for generalization. Experimental results on six benchmark datasets show MVIL's effectiveness over state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Analytic Modeling of Idle Waves in Parallel Programs: Communication, Cluster Topology, and Noise Impact 36th

Analytic Modeling of Idle Waves in Parallel Programs: Commun...

引用

36th International Conference on High Performance computing, ISC High Performance 2021

作者： Afzal, Ayesha Hager, Georg Wellein, Gerhard Erlangen National High Performance Computing Center Erlangen91058 Germany Department of Computer Science University of Erlangen-Nürnberg Erlangen91058 Germany

ISBN: (纸本)9783030787127

Most distributed-memory bulk-synchronous parallel programs in HPC assume that compute resources are available continuously and homogeneously across the allocated set of compute nodes. However, long one-off delays on individual processes can cause global disturbances, so-called idle waves, by rippling through the system. This process is mainly governed by the communication topology of the underlying parallel code. This paper makes significant contributions to the understanding of idle wave dynamics. We study the propagation mechanisms of idle waves across the processes of MPI-parallel programs. We present a validated analytic model for their propagation velocity with respect to communication parameters and topology, with a special emphasis on sparse communication patterns. We study the interaction of idle waves with MPI collectives and show that, depending on the implementation, a collective may be permeable to the wave. Finally we analyze two mechanisms of idle wave decay: topological decay, which is rooted in differences in communication characteristics among parts of the system, and noise-induced decay, which is caused by system or application noise. We show that noise-induced decay is largely independent of noise characteristics but depends only on the overall noise power. An analytic expression for idle wave decay rate with respect to noise power is derived. For model validation we use microbenchmarks and stencil algorithms on three different supercomputing platforms. © 2021, Springer Nature Switzerland AG.

关键词： Analytical models

来源：评论

学校读者我要写书评

暂无评论

Generalized upwind summation-by-parts operators and their application to nodal discontinuous Galerkin methods

arXiv

引用

arXiv 2024年

作者： Glaubitz, Jan Ranocha, Hendrik Winters, Andrew R. Schlottke-Lakemper, Michael Öffner, Philipp Gassner, Gregor Department of Aeronautics and Astronautics Massachusetts Institute of Technology United States Department of Mathematics Linköping University Sweden Institute of Mathematics Johannes Gutenberg University Mainz Germany High-Performance Scientific Computing University of Augsburg Germany High-Performance Computing Center Stuttgart Germany Institute of Mathematics TU Clausthal Germany Department of Mathematics and Computer Science Center for Data and Simulation Science University of Cologne Germany

High-order numerical methods for conservation laws are highly sought after due to their potential efficiency. However, it is challenging to ensure their robustness, particularly for under-resolved flows. Baseline high-order methods often incorporate stabilization techniques that must be applied judiciously—sufficient to ensure simulation stability but restrained enough to prevent excessive dissipation and loss of resolution. Recent studies have demonstrated that combining upwind summation-by-parts (USBP) operators with flux vector splitting can increase the robustness of finite difference (FD) schemes without introducing excessive artificial dissipation. This work investigates whether the same approach can be applied to nodal discontinuous Galerkin (DG) methods. To this end, we demonstrate the existence of USBP operators on arbitrary grid points and provide a straightforward procedure for their construction. Our discussion encompasses a broad class of USBP operators, not limited to equidistant grid points, and enables the development of novel USBP operators on Legendre–Gauss–Lobatto (LGL) points that are well-suited for nodal DG methods. We then examine the robustness properties of the resulting DG-USBP methods for challenging examples of the compressible Euler equations, such as the Kelvin–Helmholtz instability. Similar to high-order FD-USBP schemes, we find that combining flux vector splitting techniques with DG-USBP operators does not lead to excessive artificial dissipation. Furthermore, we find that combining lower-order DG-USBP operators on three LGL points with flux vector splitting indeed increases the robustness of nodal DG methods. However, we also observe that higher-order USBP operators offer less improvement in robustness for DG methods compared to FD schemes. We provide evidence that this can be attributed to USBP methods adding dissipation only to unresolved modes, as FD schemes typically have more unresolved modes than nodal DG *** Codes 65M1

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

Schema-Driven Information Extraction from Heterogeneous Tables

arXiv

引用

arXiv 2023年

作者： Bai, Fan Kang, Junmo Stanovsky, Gabriel Freitag, Dayne Dredze, Mark Ritter, Alan College of Computing Georgia Institute of Technology United States School of Computer Science and Engineering The Hebrew University of Jerusalem Artificial Intelligence Center SRI International United States Department of Computer Science Johns Hopkins University United States

In this paper, we explore the question of whether large language models can support cost-efficient information extraction from tables. We introduce schema-driven information extraction, a new task that transforms tabular data into structured records following a human-authored schema. To assess various LLM’s capabilities on this task, we present a benchmark comprised of tables from four diverse domains: machine learning papers, chemistry literature, material science journals, and webpages. We use this collection of annotated tables to evaluate the ability of open-source and API-based language models to extract information from tables covering diverse domains and data formats. Our experiments demonstrate that surprisingly competitive performance can be achieved without requiring task-specific pipelines or labels, achieving F1 scores ranging from 74.2 to 96.1, while maintaining cost efficiency. Moreover, through detailed ablation studies and analyses, we investigate the factors contributing to model success and validate the practicality of distilling compact models to reduce API reliance.1 © 2023, CC BY.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A Deep Penetration Network for Sentence Classification

SSRN

引用

SSRN 2023年

作者： Chen, Yanping Zhong, Xinyang Liu, Yijun Dong, Bo Zheng, Qinghua The College of Computer Science and Technology The Engineering Research Center of Text Computing and Cognitive Intelligence Lab Guizhou University Guizhou Guiyang550025 China Department of Computer Science and Technology Xi’an Jiaotong University Shanxi Xi’an710049 China

Sentence classification is an important task in natural language processing. In deep architectures, the task suffers from a serious semantic vanishing problem when stacking a large number of networks. To address this problem, the current methods try to enclose a mass of features with different granularities in a deep network. The main problem the methods face is that the silent feature representations are easily weakened and mixed with noisy information, which is not effective in learning contextual features and constructing semantic dependencies in a sentence. In this paper, a deep penetration network (DPN) is designed to improve deep architectures' ability to preserve the favourable semantic features. The DPN enables salient features to penetrate through deeper architectures and to construct long semantic dependencies between them. This approach is evaluated on seven public datasets. Our experiments show that the DPN exhibits a stable performance with deeper architectures. It improves the performance on three types of sentence classification tasks, outperforming the existing state-of-the-art models. © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Diversified Node Sampling based Hierarchical Transformer Pooling for Graph Representation Learning

arXiv

引用

arXiv 2023年

作者： Li, Gaichao Chen, Jinsong Hopcroft, John E. He, Kun Institute of Artificial Intelligence Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Hopcroft Center on Computing Science Huazhong University of Science and Technology Wuhan China Department of Computer Science Cornell University Ithaca United States

Graph pooling methods have been widely used on downsampling graphs, achieving impressive results on multiple graph-level tasks like graph classification and graph generation. An important line called node dropping pooling aims at exploiting learnable scoring functions to drop nodes with comparatively lower significance scores. However, existing node dropping methods suffer from two limitations: (1) for each pooled node, these models struggle to capture long-range dependencies since they mainly take GNNs as the backbones;(2) pooling only the highest-scoring nodes tends to preserve similar nodes, thus discarding the affluent information of low-scoring nodes. To address these issues, we propose a Graph Transformer Pooling method termed GTPool, which introduces Transformer to node dropping pooling to efficiently capture long-range pairwise interactions and meanwhile sample nodes diversely. Specifically, we design a scoring module based on the self-attention mechanism that takes both global context and local context into consideration, measuring the importance of nodes more comprehensively. GTPool further utilizes a diversified sampling method named Roulette Wheel Sampling (RWS) that is able to flexibly preserve nodes across different scoring intervals instead of only higher scoring nodes. In this way, GTPool could effectively obtain long-range information and select more representative nodes. Extensive experiments on 11 benchmark datasets demonstrate the superiority of GTPool over existing popular graph pooling methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Bayesian Ensembled Knowledge Extraction Strategy for Online Portfolio Selection

Bayesian Ensembled Knowledge Extraction Strategy for Online ...

引用

IEEE International Conference on Big Data

作者： Abhishek Kumar Aviv Segev Center for Ubiquitous Computing University of Oulu Oulu Finland Department of Computer Science University of Helsinki Helsinki Finland Department of Computer Science University of South Alabama Mobile USA

ISBN: (纸本)9781665480468

Online portfolio selection, one of the major fundamental problems in finance, has been explored quite extensively in recent years by machine learning and artificial intelligence communities. Recent state-of-the-art methods have focused on Mean Reversion significantly and have demonstrated outstanding performance. Another version of the same phenomenon, Median Reversion, has also performed well and demonstrated its ability to be robust against noises and outliers. Another important characteristic is Momentum. In this paper, a Bayesian ensembling approach to extract knowledge from both Mean Reversion and Median Reversion simultaneously based on the momentum associated with each one is proposed for the online portfolio selection task. The proposed method demonstrates its effectiveness by outperforming current state-of-the-art algorithms on several datasets.

关键词： Computational modeling Stacking Finance Big Data Data models Bayes methods High frequency

来源：评论

学校读者我要写书评

暂无评论

Quantum Hamiltonian Descent for Non-smooth Optimization

arXiv

引用

arXiv 2025年

作者： Leng, Jiaqi Zheng, Yufan Jia, Zhiyuan Fan, Lei Zhao, Chaoyue Peng, Yuxiang Wu, Xiaodi Simons Institute for the Theory of Computing University of California Berkeley United States Department of Mathematics University of California Berkeley United States Department of Computer Science University of Maryland College Park United States Joint Center for Quantum Information and Computer Science University of Maryland United States Department of Applied Mathematics University of Washington United States Department of Engineering Technology University of Houston United States Department of Electrical and Computer Engineering University of Houston United States Department of Industrial and Systems Engineering University of Washington United States Artephi Computing Inc United States

Non-smooth optimization models play a fundamental role in various disciplines, including engineering, science, management, and finance. However, classical algorithms for solving such models often struggle with convergence speed, scalability, and parameter tuning, particularly in high-dimensional and non-convex settings. In this paper, we explore how quantum mechanics can be leveraged to overcome these limitations. Specifically, we investigate the theoretical properties of the Quantum Hamiltonian Descent (QHD) algorithm for non-smooth optimization in both continuous and discrete time. First, we propose continuous-time variants of the general QHD algorithm and establish their global convergence and convergence rate for non-smooth convex and strongly convex problems through a novel Lyapunov function design. Furthermore, we prove the finite-time global convergence of continuous-time QHD for non-smooth non-convex problems under mild conditions (i.e., locally Lipschitz). In addition, we propose discrete-time QHD, a fully digitized implementation of QHD via operator splitting (i.e., product formula). We find that discrete-time QHD exhibits similar convergence properties even with large time steps. Finally, numerical experiments validate our theoretical findings and demonstrate the computational advantages of QHD over classical non-smooth non-convex optimization algorithms. Copyright © 2025, The Authors. All rights reserved.

关键词： Continuous time systems

来源：评论

学校读者我要写书评

暂无评论

A 3D Memristive Cubic Map with Dual Discrete Memristors: Design, Implementation, and Application in Image Encryption

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Gao, Suo Iu, Herbert Ho-Ching Erkan, Ugur Simsek, Cemaleddin Toktas, Abdurrahim Cao, Yinghong Wu, Rui Mou, Jun Li, Qi Wang, Chunpeng Dalian Polytechnic University School of Information Science and Engineering Dalian116034 China The University of Western Australia School of Electrical Electronic and Computer Engineering Perth6009 Australia Faculty of Engineering Electrical and Electronics Engineering Respectively Karamanoglu Mehmetbey University Karaman70200 Turkey Ankara University Engineering Faculty Department of Artificial Intelligence and Data Engineering Ankara06830 Turkey Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan250000 China

Discrete chaotic systems based on memristors exhibit excellent dynamical properties and are more straightforward to implement in hardware, making them highly suitable for generating cryptographic keystreams. However, most existing memristor-based chaotic systems rely on a single memristor. This paper introduces a novel discrete chaotic system employing dual memristors, named the 3D memristive cubic map with dual discrete memristors (3D-MCM). The 3D-MCM system demonstrates richer and more intricate dynamical behaviors compared to its single-memristor counterparts, as verified through bifurcation diagrams, Lyapunov exponent spectra, and complexity analyses. Notably, the system exhibits coexisting attractors, substantially enhancing its dynamical complexity. Hardware implementation of the 3D-MCM attractors confirms its feasibility for industrial applications. To illustrate the system's potential in encryption tasks, this study integrates the quaternary-based permutation and dynamic emanating diffusion (QPDED-IE) scheme for image encryption with the *** results demonstrate that the QPDED-IE scheme based on the 3D-MCM exhibits strong diffusion and confusion properties, effectively resisting cryptanalytic attacks. © 1991-2012 IEEE.

关键词： Bifurcation (mathematics)

来源：评论

学校读者我要写书评

暂无评论

SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning

arXiv

引用

arXiv 2023年

作者： Chen, Jinsong Li, Gaichao Hopcroft, John E. He, Kun Institute of Artificial Intelligence Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Hopcroft Center on Computing Science Huazhong University of Science and Technology Wuhan China Department of Computer Science Cornell University Ithaca United States

The emerging graph Transformers have achieved impressive performance for graph representation learning over graph neural networks (GNNs). In this work, we regard the self-attention mechanism, the core module of graph Transformers, as a two-step aggregation operation on a fully connected graph. Due to the property of generating positive attention values, the self-attention mechanism is equal to conducting a smooth operation on all nodes, preserving the low-frequency information. However, only capturing the low-frequency information is inefficient in learning complex relations of nodes on diverse graphs, such as heterophily graphs where the high-frequency information is crucial. To this end, we propose a Signed Attention-based Graph Transformer (SignGT) to adaptively capture various frequency information from the graphs. Specifically, SignGT develops a new signed self-attention mechanism (SignSA) that produces signed attention values according to the semantic relevance of node pairs. Hence, the diverse frequency information between different node pairs could be carefully preserved. Besides, SignGT proposes a structure-aware feed-forward network (SFFN) that introduces the neighborhood bias to preserve the local topology information. In this way, SignGT could learn informative node representations from both long-range dependencies and local topology information. Extensive empirical results on both node-level and graph-level tasks indicate the superiority of SignGT against state-of-the-art graph Transformers as well as advanced GNNs. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

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：