检索结果-内蒙古大学图书馆

11th International Conference on Information Technology and Quantitative Management, ITQM 2024

作者： Xu, Ruijie Shi, Yong Qi, Zhiquan School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Research Center on Fictitious Economy and Data Science University of Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China College of Information Science and Technology University of Nebraska Omaha68182 United States

In the realm of visual tasks, the estimation of orientation plays a pivotal role yet often remains an understudied aspect in the gamut of image analysis research. This paper endeavors to address this deficiency by conducting a comprehensive review of methods for orientation estimation within 2D imaging contexts. We aim to provide researchers with an exhaustive overview and detailed analysis of the techniques utilized for orientation estimation, thereby enhancing their understanding of this complex field. We introduce an organized classification of orientation estimation methods, segmented into approaches based on classification algorithms and those based on regression models. This classification not only sheds light on the distinct methodologies but also scrutinizes their underlying assumptions, practical applications. Additionally, the study identifies and underscores emerging research opportunities that hold the potential to enrich the discourse and technical advancements in orientation estimation, thereby encouraging deeper academic investigation and technological development. © 2024 The Authors.

关键词： Classification-based Orientation Estimation Regression-based Orientation Estimation

来源：评论

学校读者我要写书评

暂无评论

Latest Technologies on dataset Distillation: A Survey 11

Latest Technologies on Dataset Distillation: A Survey

引用

11th International Conference on Information Technology and Quantitative Management, ITQM 2024

作者： Li, Muyang Qu, Yi Shi, Yong Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States

dataset distillation refers to the process of constructing a smaller dataset based on a larger dataset, so that the training model with the smaller dataset can obtain similar results to the larger dataset. In this paper, we first briefly review the basic methods and some recent advances in this field from the perspectives of meta-learning framework and data matching framework, including the backpropagation through time(BPTT), kernel ridge regression(KRR), decoupled techniques, gradient matching(DC), trajectory matching(MTT) and distribution matching(DM). The results of the plug-and-play approach in recent years are then presented. Finally, we discuss possible future developments from the perspectives of data distillation algorithms on large datasets, the relationship between compress ratio and information contained, more tasks and data modalities, and the use of generative models to improve the distillation results of datasets. © 2024 The Authors.

关键词： data assimilation

来源：评论

学校读者我要写书评

暂无评论

WATuning:A Workload-Aware Tuning System with Attention-Based Deep Reinforcement Learning

引用

Journal of Computer Science & Technology 2021年第4期36卷 741-761页

作者： Jia-Ke Ge Yan-Feng Chai Yun-Peng Chai Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing 100872China School of Information Renmin University of ChinaBeijing 100872China College of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030027China

Configuration tuning is essential to optimize the performance of systems(e.g.,databases,key-value stores).High performance usually indicates high throughput and low *** present,most of the tuning tasks of systems are performed artificially(e.g.,by database administrators),but it is hard for them to achieve high performance through tuning in various types of systems and in various *** recent years,there have been some studies on tuning traditional database systems,but all these methods have some *** this article,we put forward a tuning system based on attention-based deep reinforcement learning named WATuning,which can adapt to the changes of workload characteristics and optimize the system performance efficiently and ***,we design the core algorithm named ATT-Tune for WATuning to achieve the tuning task of *** algorithm uses workload characteristics to generate a weight matrix and acts on the internal metrics of systems,and then ATT-Tune uses the internal metrics with weight values assigned to select the appropriate ***,WATuning can generate multiple instance models according to the change of the workload so that it can complete targeted recommendation services for different types of ***,WATuning can also dynamically fine-tune itself according to the constantly changing workload in practical applications so that it can better fit to the actual environment to make *** experimental results show that the throughput and the latency of WATuning are improved by 52.6%and decreased by 31%,respectively,compared with the throughput and the latency of CDBTune which is an existing optimal tuning method.

关键词： attention mechanism auto-tuning system reinforcement learning(RL) workload-aware

来源：评论

学校读者我要写书评

暂无评论

PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering

arXiv

引用

arXiv 2024年

作者： Xu, Fangzhi Lin, Qika Zhao, Tianzhe Han, Jiawei Liu, Jun School of Computer Science and Technology Xi’an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering China

Logical reasoning task has attracted great interest since it was proposed. Faced with such a task, current competitive models, even large language models (e.g., ChatGPT and PaLM 2), still perform badly. Previous promising LMs struggle in logical consistency modeling and logical structure perception. To this end, we model the logical reasoning task by transforming each logical sample into reasoning paths and propose an architecture PathReasoner. It addresses the task from the views of both data and model. To expand the diversity of the logical samples, we propose an atom extension strategy supported by equivalent logical formulas, to form new reasoning paths. From the model perspective, we design a stack of transformer-style blocks. In particular, we propose a path-attention module to joint model in-atom and cross-atom relations with the high-order diffusion strategy. Experiments show that PathReasoner achieves competitive performances on two logical reasoning benchmarks and great generalization abilities. © 2024, CC BY.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Neural Network for Solving Nonlinear Parabolic Differential Equations 6

Neural Network for Solving Nonlinear Parabolic Differential ...

引用

2022 6th International Conference on Mechanics, Mathematics and Applied Physics, ICMMAP 2022

作者： Zhang, Hong Huang, Hongying School of Information Engineering Zhejiang Ocean University Zhejiang Zhoushan316000 China Key Laboratory of Oceanographic Big Data Mining and Application of Zhejiang Province Zhejiang Zhoushan316000 China

We develop a cell-average-based neural network (CANN) method to compute nonlinear differential equations. Using feedforward networks, we can train average solutions from t0 + "t with initial values. In order to find the optimal parameters for the network, in combination with supervised training, we use a BP algorithm. By the trained network, we may compute the approximate solutions at the time t n+1 with the ones at time tn . Numerical results show CANN method permits a very large time step size for solution evolution. © Published under licence by IOP Publishing Ltd.

关键词： Differential equations

来源：评论

学校读者我要写书评

暂无评论

Structure Aware Loss for Deep Unsupervised Industrial Image Registration 24

Structure Aware Loss for Deep Unsupervised Industrial Image ...

引用

24th IEEE International Conference on data mining Workshops, ICDMW 2024

作者： Shi, Yong Lyu, Mengjin Qi, Zhiquan Chinese Academy of Sciences Research Center on Fictitious Economy and Data Science Beijing100190 China Chinese Academy of Sciences Key Laboratory of Big Data Mining and Knowledge Management Beijing100190 China University of Nebraska at Omaha College of Information Science and Technology OmahaNE 68182 United States University of Chinese Academy of Sciences School of Computer Science and Technology Beijing100190 China University of Chinese Academy of Sciences School of Economics and Management Beijing100190 China

ISBN: (纸本)9798331530631

Image registration is extensively utilized in industrial applications. However, specific challenges inherent to these environments - such as low texture, significant displacement, and poor lighting conditions - complicate the registration process. This paper introduces a structure-aware loss module tailored to the unique characteristics of industrial images. This module promotes the network's focus on salient regions while emphasizing structural features. Additionally, it is designed as a plug-in component, facilitating integration with any loss function and homography estimation method. We develop an unsupervised registration network and create an industrial dataset to evaluate the module's effectiveness. A series of experiments demonstrate that our structure-aware module significantly enhances registration performance. © 2024 IEEE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

OmniSQL: Synthesizing High-quality Text-to-SQL data at Scale

arXiv

引用

arXiv 2025年

作者： Li, Haoyang Wu, Shang Zhang, Xiaokang Huang, Xinmei Zhang, Jing Jiang, Fuxin Wang, Shuai Zhang, Tieying Chen, Jianjun Shi, Rui Chen, Hong Li, Cuiping Engineering Research Center of Database and Business Intelligence MOE China School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering MOE China ByteDance Inc China

Text-to-SQL, the task of translating natural language questions into SQL queries, plays a crucial role in enabling non-experts to interact with databases. While recent advancements in large language models (LLMs) have significantly enhanced text-to-SQL performance, existing approaches face notable limitations in real-world text-to-SQL applications. Prompting-based methods often depend on closed-source LLMs, which are expensive, raise privacy concerns, and lack customization. Fine-tuning-based methods, on the other hand, suffer from poor generalizability due to the limited coverage of publicly available training data. To overcome these challenges, we propose a novel and scalable text-to-SQL data synthesis framework for automatically synthesizing large-scale, high-quality, and diverse datasets without extensive human intervention. Using this framework, we introduce SynSQL-2.5M, the first million-scale text-to-SQL dataset, containing 2.5 million samples spanning over 16,000 synthetic databases. Each sample includes a database, SQL query, natural language question, and chain-of-thought (CoT) solution. Leveraging SynSQL-2.5M, we develop OmniSQL, a powerful open-source text-to-SQL model available in three sizes: 7B, 14B, and 32B. Extensive evaluations across nine datasets demonstrate that OmniSQL achieves state-of-the-art performance, matching or surpassing leading closed-source and open-source LLMs, including GPT-4o and DeepSeek-V3, despite its smaller size. We release all code, datasets, and models to support further research. Copyright © 2025, The Authors. All rights reserved.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Achieving high carrier mobility and low lattice thermal conductivity in GeTe-based alloys by cationic/anionic co-doping

引用

Rare Metals 2024年第6期43卷 2784-2795页

作者： Xiao-Qiang Wang Xiao-Quan Hu Jun-Yan Lin Chu-Bin Li Xiao-Tong Yu Qi-Yong Chen Li-Li Xi Qi-Shuo Yang Han Li Ji-Ye Zhang Shuan-Kui Li Kai Guo School of Physics and Materials Science Guangzhou UniversityGuangzhou 510006China Research Center for Advanced Information Materials(CAIM) Huangpu Research&Graduate School of Guangzhou UniversitySino-Singapore Guangzhou Knowledge CityGuangzhou510555China School of Materials Science and Engineering Shanghai UniversityShanghai 200444China Materials Genome Institute Shanghai UniversityShanghai 200444China School of Mechanical and Mining Engineering University of QueenslandBrisbaneQLD 4072Australia Key Laboratory of Si-Based Information Materials&Devices and Integrated Circuits Design Department of Education of Guangdong ProvinceGuangzhou 510006China

TheⅣ-Ⅵcompound GeTe is considered as a promising alternative to the toxic PbTe for high-efficiency mid-temperature thermoelectric ***,pristine GeTe suffers from a high concentration of Ge vacancies,resulting in an excessively high hole concentration(>1×10^(21)cm^(-3)),which greatly limits its thermoelectric *** address this issue,CuBiTe_(2)alloying is introduced to increase the formation energy of Ge vacancies in GeTe,thereby inhibiting the high carrier *** carrier scattering caused by the electronegativity difference between different elements is suppressed due to the similar electronegativity of Cu and Ge atoms.A relatively high hole mobility is obtained,which ultimately leads to a high power ***,by introducing Se as an alloying element at the anionic site in GeTe,dense point defects with mass/strainfield fluctuations are *** contributes to the strengthening of phonon scattering,thereby reducing the lattice thermal conductivity from 1.44 W·m^(-1)·K^(-1)for pristine GeTe to 0.28 W·m^(-1)·K^(-1)for Ge_(0.95)Cu_(0.05)Bi_(0.05)Te_(0.9)Se_(0.15)compound at 623 K.

关键词： GeTe Carrier mobility CuBiTe_(2)alloying Lattice thermal conductivity Thermoelectric properties

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks with Learnable and Optimal Polynomial Bases

arXiv

引用

arXiv 2023年

作者： Guo, Yuhe Wei, Zhewei Gaoling School of Articial Intelligence Renmin University of China China Peng Cheng Laboratory China Beijing Key Laboratory of Big Data Management and Analysis Methods China MOE Key Lab of Data Engineering and Knowledge Engineering China

Polynomial filters, a kind of Graph Neural Networks, typically use a predetermined polynomial basis and learn the coefficients from the training data. It has been observed that the effectiveness of the model is highly dependent on the property of the polynomial basis. Consequently, two natural and fundamental questions arise: Can we learn a suitable polynomial basis from the training data? Can we determine the optimal polynomial basis for a given graph and node features? In this paper, we propose two spectral GNN models that provide positive answers to the questions posed above. First, inspired by Favard’s Theorem, we propose the FavardGNN model, which learns a polynomial basis from the space of all possible orthonormal bases. Second, we examine the supposedly unsolvable definition of optimal polynomial basis from Wang & Zhang (2022) and propose a simple model, OptBasisGNN, which computes the optimal basis for a given graph structure and graph signal. Extensive experiments are conducted to demonstrate the effectiveness of our proposed models. Our code is available at https://***/yuziGuo/FarOptBasis. © 2023, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Effectiveness of Carbon Emission Trading Market in China 10

Analysis of the Effectiveness of Carbon Emission Trading Mar...

引用

10th International Conference on Information Technology and Quantitative Management, ITQM 2023

作者： Yu, Anqi Peng, Shuyang Li, Yizhi Guo, Kun School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Dornslife School of Arts and Science University of Southern California Los AngelesCA90007 United States Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China

As global climate change intensifies, carbon emissions trading has become an important tool for countries to address climate change. China, as the world's largest carbon emitter, has been conducting carbon trading pilots since 2011, and officially launched a national carbon market in 2017. The construction of China's carbon market is crucial for China and global efforts to address climate change. Market efficiency is a key indicator of its success. This article aims to measure and analyze the effectiveness of China's carbon market, and to explore policy measures to enhance its effectiveness. It selected data from effective trading days and conducted an exploratory study on the effectiveness of China's pilot carbon markets. To analyze the effectiveness of the carbon market, we combined the efficient market hypothesis theory with the fractal market hypothesis theory, adopted the variance ratio test method, and the rescaled range analysis method to conduct a comprehensive analysis of the Chinese carbon market, while also accounting for the reasons behind their computational inconsistency. As our research shows that China's pilot carbon market has not reached the weak efficiency level, we have provided some suggestions based on the current operational status of China's carbon market. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Tenth International Conference on Information Technology and Quantitative Management.

关键词： Carbon

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：