检索结果-内蒙古大学图书馆

IEEE International Conference on Data Mining (ICDM)

作者： Li Sun Zhenhao Huang Hua Wu Junda Ye Hao Peng Zhengtao Yu Philip S. Yu School of Control and Computer Engineering North China Electric Power University Beijing China School of Computer Science Beijing University of Posts and Telecommunications Beijing China State Key Laboratory of Software Development Environment Beihang University Beijing China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming China Department of Computer Science University of Illinois at Chicago IL USA

Graph Neural Networks (GNNs) have shown great power for learning and mining on graphs, and Graph Structure Learning (GSL) plays an important role in boosting GNNs with a refined graph. In the literature, most GSL solutions either primarily focus on structure refinement with task-specific supervision (i.e., node classification), or overlook the inherent weakness of GNNs themselves (e.g., over-squashing), resulting in suboptimal performance despite sophisticated designs. In light of these limitations, we propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs. In this paper, we take a fundamentally different perspective of the Ricci curvature in Riemannian geometry, in which we encounter the challenges of modeling, utilizing and computing Ricci curvature. To tackle these challenges, we present a self-supervised Riemannian model, DeepRicci. Specifically, we introduce a latent Riemannian space of heterogeneous curvatures to model various Ricci curvatures, and propose a gyrovector feature mapping to utilize Ricci curvature for typical GNNs. Thereafter, we refine node features by geometric contrastive learning among different geometric views, and simultaneously refine graph structure by backward Ricci flow based on a novel formulation of differentiable Ricci curvature. Finally, extensive experiments on public datasets show the superiority of DeepRicci, and the connection between backward Ricci flow and over-squashing. Codes of our work are given in https://***/RiemanGraph/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Duality-Based Approach to Inverse Kalman Filtering

引用

IFAC-PapersOnLine 2023年第2期56卷 10258-10263页

作者： Yibei Li Bo Wahlberg Lihua Xie Xiaoming Hu School of Electrical and Electronic Engineering Nanyang Technological University Singapore Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Division of Optimization and Systems Theory Department of Mathematics KTH Royal Institute of Technology Stockholm Sweden

In this paper, the inverse Kalman filtering problem is addressed using a duality-based framework, where certain statistical properties of uncertainties in a dynamical model are recovered from observations of its posterior estimates. The duality relation in inverse filtering and inverse optimal control is established. It is shown that the inverse Kalman filtering problem can be solved using results from a well-posed inverse linear quadratic regulator. Identifiability of the considered inverse filtering model is proved and a unique covariance matrix is recovered by a least squares estimator, which is also shown to be statistically consistent. Effectiveness of the proposed methods is illustrated by numerical simulations.

关键词： Inverse filtering Kalman filters duality covariance estimation identifiability

来源：评论

学校读者我要写书评

暂无评论

Global solution to sensor network localization: A non-convex potential game approach and its distributed implementation

arXiv

引用

arXiv 2024年

作者： Xu, Gehui Chen, Guanpu Hong, Yiguang Fidan, Baris Parisini, Thomas Johansson, Karl H. Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Beijing100190 China The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden Department of Control Science and Engineering Tongji University Shanghai201804 China Shanghai Research Institute for Intelligent Autonomous Systems Shanghai201210 China The Department of Mechanical and Mechatronics Engineering University of Waterloo WaterlooONN2L 3G1 Canada The Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom The Department of Engineering and Architecture University of Trieste Trieste34127 Italy

Consider a sensor network consisting of both anchor and non-anchor nodes. We address the following sensor network localization (SNL) problem: given the physical locations of anchor nodes and relative measurements among all nodes, determine the locations of all non-anchor nodes. The solution to the SNL problem is challenging due to its inherent non-convexity. In this paper, the problem takes on the form of a multi-player nonconvex potential game in which canonical duality theory is used to define a complementary dual potential function. After showing the Nash equilibrium (NE) correspondent to the SNL solution, we provide a necessary and sufficient condition for a stationary point to coincide with the NE. An algorithm is proposed_ to reach the NE and shown to have convergence rate O(1/√k). With the aim of reducing the information exchange within a network, a distributed algorithm for NE seeking is implemented and its global convergence analysis is provided. Extensive simulations show the validity and effectiveness of the proposed approach to solve the SNL problem. Copyright © 2024, The Authors. All rights reserved.

关键词： Game theory

来源：评论

学校读者我要写书评

暂无评论

Awakened at CheckThat! 2022: Fake News Detection using BiLSTM and Sentence Transformer

Awakened at CheckThat! 2022: Fake News Detection using BiLST...

引用

2022 Conference and Labs of the Evaluation Forum, CLEF 2022

作者： Truică, Ciprian-Octavian Apostol, Elena-Simona Paschke, Adrian Department of Information Technology Uppsala University Lägerhyddsvägen 1 Uppsala75105 Sweden Computer Science and Engineering Department Faculty of Automatic Control and Computers University Politehnica of Bucharest Splaiul Independentei 313 Bucharest060042 Romania Fraunhofer Institute for Open Communication Systems Berlin10589 Germany

In recent years, online social networks and online news venues have become some of the main news and event-related information spreading mediums. Although using these mediums has facilitated the speed of accessing information, it also created a new phenomenon used for propaganda and disinformation: fake news. As fake news has detrimental consequences to society, new technologies need to be developed in order to stop their harmful effects. In this paper, we propose two Bidirectional Long Short-Term Memory (BiLSTM) architectures with sentence transformers to solve two tasks: (1) a multi-class mono-lingual fake news detection task (i.e., mono-lingual task);and (2) a multi-class cross-lingual fake news detection task (i.e., cross-lingual task). For the mono-lingual task, we train and test a BiLSTM with BART sentence transformers model on an English dataset and obtain an accuracy of ∼ 0.53 and an F1-Score of ∼ 0.32. For the cross-lingual task, we train a BiLSTM with XLM sentence transformers model on an English dataset and test the model using transfer learning on a German dataset. For this task, we obtain an accuracy of ∼ 0.28 and an F1-Score of ∼ 0.19. © 2022 Copyright for this paper by its authors.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

Joint Data Compression and Task Scheduling for LEO Satellite Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： He, Lijun Li, Shiyin Jia, Ziye Wang, Juncheng Han, Zhu China University of Mining and Technology School of Information and Control Engineering Xuzhou221116 China Xidian University State Key Laboratory of Integrated Services Networks Shaanxi Xi'an710071 China Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing210000 China Hong Kong Baptist University Department of Computer Science China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

We investigate a joint data compression and task scheduling problem for Low Earth Orbit Satellite Networks (LEOSNs), to maximize the sum weights of tasks while simultaneously minimizing the total data loss. First, we propose a novel Multi-Resource Conflict Graph (MRCG) model to characterize the intertwined communication and computation allocation conflicts inherent in typical data offloading processes of LEOSNs. Leveraging the proposed MRCG model, we then formulate the studied problem for LEOSNs as a linear integer program, to maximize the normalized weighted sum of both the sum task weight and the total data loss. We further explore the intrinsic structure of the linear integer program to propose an efficient solution using the Semi-Definite Relaxation (SDR) technique. Finally, the simulation results underscore that the synergistic optimization of data compression and task scheduling significantly facilitates the data offloading efficiency of LEOSNs, and the performances surpass existing benchmarks across a broad range of system parameters. © 1967-2012 IEEE.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

Leveraging GPT-4 Capabilities for Developing Context-Aware, Personalized Chatbot Interfaces in E-commerce Customer Support Systems

Leveraging GPT-4 Capabilities for Developing Context-Aware, ...

引用

International Conference on Communications and Signal Processing

作者： Kathari Santosh Timur Kholmukhamedov M Sandeep Kumar Mohd Aarif Iskandar Muda B Kiran Bala Department of MBA CMR Institute of Technology Bengaluru Bengaluru India Automatic Control and Computer Engineering Department Turin Polytechnic University in Tashkent Tashkent Uzbekistan Publishing Global Research Network Noida India Universitas Sumatera Utara Medan Indonesia Department of Artificial Intelligence and Data Science K.Ramakrishnan college of Engineering Trichy

ISBN: (数字)9798350353068

ISBN: (纸本)9798350353075

In the realm of e-commerce customer support, the adoption of chatbots is on the rise, driven by a quest for heightened user interactions. This study introduces an inventive approach harnessing the advanced capabilities of GPT-4 to construct chatbot interfaces that are both context-aware and personalized. The main aim of this work is to revolutionize ecommerce customer support by developing intelligent and adaptable chatbot interfaces that are context-aware, personalized, and significantly enhance user experiences. Existing chatbot models struggle with context retention and personalization, limiting effectiveness in dynamic e-commerce environments despite the promise of automation. This innovative approach leverages GPT-4’s robust language processing, integrating it with user profiling systems for personalized responses grounded in user preferences and historical interactions. The method gives, diverse e-commerce dataset undergoes collection and pre-processing, followed by fine-tuning GPT-4 with an emphasis on context-awareness and personalized responses. The model is seamlessly integrated with e-commerce backend systems for real-time information, multimodal input support caters to varied user preferences. Results exhibit a significant 95% accuracy improvement, affirming the chatbot’s enhanced ability to comprehend user queries. By integrating personalization and advanced context retention, this study enhances user engagement, paving way for revolutionary intelligent and adaptable chatbot interfaces in ecommerce customer support.

关键词： Ethics Limiting Automation Biological system modeling Customer services Companies Chatbots

来源：评论

学校读者我要写书评

暂无评论

Kernel-Based Learning of Stable Nonlinear State-Space Models

Kernel-Based Learning of Stable Nonlinear State-Space Models

引用

IEEE Conference on Decision and control

作者： M.F. Shakib R. Tóth A.Y. Pogromsky A. Pavlov N. van de Wouw Department of Electrical and Electronic Engineering Imperial College London London United Kingdom Department of Mechanical Engineering Eindhoven University of Technology Eindhoven The Netherlands Department of Electrical Engineering Eindhoven University of Technology Eindhoven The Netherlands Institute for Computer Science and Control Budapest Hungary Department of Geoscience and Petroleum NTNU Trondheim Norway

This paper presents a kernel-based learning approach for black-box nonlinear state-space models with a focus on enforcing model stability. Specifically, we aim to enforce a stability notion called convergence which guarantees that, for any bounded input from a user-defined class, the model responses converge to a unique steady-state solution that remains within a positively invariant set that is user-defined and bounded. Such a form of model stability provides robustness of the learned models to new inputs unseen during the training phase. The problem is cast as a convex optimization problem with convex constraints that enforce the targeted convergence property. The benefits of the approach are illustrated by a simulation example.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Theory of phase reduction for systems with higher-order interactions: a route to Kuramoto models on hypergraphs

arXiv

引用

arXiv 2025年

作者： León, Iván Muolo, Riccardo Hata, Shigefumi Nakao, Hiroya Department of Applied Mathematics and Computer Science Universidad de Cantabria Santander39005 Spain Department of Systems and Control Engineering Tokyo Institute of Technology Tokyo152-8552 Japan Graduate School of Science and Engineering Kagoshima University Kagoshima890-0065 Japan Research Center for Autonomous Systems Materialogy Institute of Innovative Research Tokyo Institute of Technology Yokohama226-8501 Japan

Phase reduction is a powerful technique in the study of nonlinear oscillatory systems. Under certain assumptions, it allows us to describe each multidimensional oscillator by a single phase variable, giving rise to simple phase models such as the Kuramoto model. Classically, the method has been applied in the case where the interactions are only pairwise (two-body). However, increasing evidence shows that interactions in real-world systems are not pairwise but higher-order, i.e., many-body. Although synchronization in higher-order systems has received much attention, analytical results are scarce because of the highly nonlinear nature of the framework. In this paper, we fill the gap by presenting a general theory of phase reduction for the case of higher-order interactions. We show that the higher-order topology is preserved in the phase reduced model at the first order and that only odd couplings have an effect on the dynamics when certain symmetries are present. Additionally, we show the power and ductility of the phase reduction approach by applying it to a population of Stuart-Landau oscillators with an all-to-all configuration and with a ring-like hypergraph topology;in both cases, only the analysis of the phase model can provide insights and analytical results. © 2025, CC BY-NC-ND.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Investigation of Automatic Part-of-Speech Tagging using CRF, HMM and LSTM on Misspelled and Edited Texts 5

Investigation of Automatic Part-of-Speech Tagging using CRF,...

引用

5th Artificial Intelligence and Cloud Computing Conference, AICCC 2022

作者： Aydinov, Farhad Huseynov, Igbal Sayadzada, Sofiya Rustamov, Samir Data Science University of Glasgow United Kingdom Computational Linguistics and Language Technologies Charles University Prague Czech Republic Department of Applied Mathematics and Computer Science Technical University of Denmark Copenhagen Denmark School of Information Technology and Engineering ADA University Baku Azerbaijan Institute of Control Systems BakuVarna Bulgaria Azerbaijan

ISBN: (纸本)9781450398749

Part-of-speech tagging is the process of assigning words in a given text to appropriate parts-of speech in order to reduce the disambiguation which may arise depending on the contextual usage of the words. In this paper, the problem of word sense disambiguation in Azerbaijani language is addressed by applying part of speech tagging on two varying data corpora, misspelled, and edited (clean) text using 3 different machine learning algorithms: Hidden Markov Model, Long Short-Term Memory, and Conditional Random Fields. The comparative analysis on the outcomes of the mentioned algorithms and their accuracy scores were analysed in the paper. The misspelled dataset for the experiments is provided by Unibank from their chatbot dialogues while the clean textual data was retrieved from the books and newspapers in Azerbaijani. The experiments showed that the Bidirectional LSTM has the highest accuracy scores for both edited (98.2%) and noisy (96.2%) data corpora. Suggested models can be used in the application of algorithms focuses on part of speech tags and syntactic structure of Azerbaijani language which is an agglutinative language belonging to Turkic languages family, thus enabling the research to be further investigated in other agglutinative languages with similar grammatical structure. © 2022 ACM.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

ERROR ANALYSIS OF KERNEL EDMD FOR PREDICTION AND control IN THE KOOPMAN FRAMEWORK

arXiv

引用

arXiv 2023年

作者： Philipp, Friedrich Schaller, Manuel Worthmann, Karl Peitz, Sebastian Nüske, Feliks Technische Universität Ilmenau Optimization-Based Control Group Institute for Mathematics Ilmenau Germany Optimization-Based Control Group Institute of Mathematics Technische Universität Ilmenau Ilmenau Germany Paderborn University Department of Computer Science Data Science for Engineering Germany Max Planck Institute for Dynamics of Complex Technical Systems Magdeburg Germany Department of Mathematics and Computer Science Freie Universität Berlin Germany

Extended Dynamic Mode Decomposition (EDMD) is a popular data-driven method to approximate the Koopman operator for deterministic and stochastic (control) systems. This operator is linear and encompasses full information on the (expected stochastic) dynamics. In this paper, we analyze a kernel-based EDMD algorithm, known as kEDMD, where the dictionary consists of the canonical kernel features at the data points. The latter are acquired by i.i.d. samples from a user-defined and application-driven distribution on a compact set. We prove bounds on the prediction error of the kEDMD estimator when sampling from this (not necessarily ergodic) distribution. The error analysis is further extended to control-affine systems, where the considered invariance of the Reproducing Kernel Hilbert Space is significantly less restrictive in comparison to invariance assumptions on an a-priori chosen dictionary. © 2023, CC BY.

关键词： Dynamic mode decomposition

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：