检索结果-内蒙古大学图书馆

FOURIER NEURAL SOLVER FOR LARGE SPARSE LINEAR ALGEBRAIC SYSTEMS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Cui, Chen Jiang, Kai Liu, Yun Shu, Shi Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

Large sparse linear algebraic systems can be found in a variety of scientific and engineering fields, and many scientists strive to solve them in an efficient and robust manner. In this paper, we propose an interpretable neural solver, the Fourier Neural Solver (FNS), to address them. FNS is based on deep learning and Fast Fourier transform. Because the error between the iterative solution and the ground truth involves a wide range of frequency modes, FNS combines a stationary iterative method and frequency space correction to eliminate different components of the error. Local Fourier analysis reveals that the FNS can pick up on the error components in frequency space that are challenging to eliminate with stationary methods. Numerical experiments on the anisotropy diffusion equation, convection-diffusion equation, and Helmholtz equation show that FNS is more efficient and more robust than the state-of-the-art neural *** Codes 65F10 65N22 68T07 35Q68 Copyright © 2022, The Authors. All rights reserved.

关键词： Fourier analysis

Examination of the Multimodal Nature of Multi-Objective Neural Architecture Search

学校读者我要写书评

暂无评论

Examination of the Multimodal Nature of Multi-Objective Neur...

2023 IEEE Symposium Series on computational Intelligence, SSCI 2023

作者： Gong, Cheng Nan, Yang Pang, Lie Meng Ishibuchi, Hisao Zhang, Qingfu Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China City University of Hong Kong Department of Computer Science Kowloon Tong Hong Kong The City University of Hong Kong Shenzhen Research Institute Shenzhen China

ISBN: (纸本)9781665430654

Remarkable successes in deep learning have spurred significant growth in the field of neural architecture search (NAS), which is rapidly advancing as a promising technique for automating the design of network architecture. From an optimization standpoint, a NAS task for a given search space can be viewed as a multi-objective optimization problem (MOP) when considering multiple design criteria simultaneously (e.g., prediction accuracy, architecture complexity, hardware efficiency). However, whether a NAS problem is a multimodal multi-objective optimization problem or not (i.e., whether a single non-dominated solution in the objective space has multiple different neural network architectures or not) has not been examined in the literature. This presents an intriguing research question that merits further investigation. To fill this gap, we examine the multimodal nature of seven multi-objective NAS problems. By doing so, this work aims to help MOP researchers to better understand the characteristics of the multi-objective NAS problems. © 2023 IEEE.

关键词： Multi-objective optimization Multimodal multi-objective optimization Neural architecture search

Initial Populations with a Few Heuristic Solutions Significantly Improve Evolutionary Multi-Objective Combinatorial Optimization

学校读者我要写书评

暂无评论

Initial Populations with a Few Heuristic Solutions Significa...

2023 IEEE Symposium Series on computational Intelligence, SSCI 2023

ISBN: (纸本)9781665430654

Population initialization is a crucial and essential step in evolutionary multi-objective optimization (EMO) algorithms. The quality of the generated initial population can significantly affect the performance of an EMO algorithm. However, few studies have focused on designing a generalized initialization method to improve the performance of EMO algorithms in solving multi-objective combinatorial optimization (MOCO) problems. Most of the existing advanced initialization methods involve complex techniques tailored to the specific characteristics of the problems to be solved. In this paper, we propose a general and effective framework of population initialization for EMO algorithms, aiming to improve their performances in solving various MOCO problems. Our approach involves the inclusion of a few specific heuristic solutions, including extreme solutions and a center solution, into the initial population. This inclusion serves to guide the evolution of the population throughout the optimization process. Our experimental results show that initial populations with a few heuristic solutions significantly improve the performance of EMO algorithms. Algorithm behavior analysis and further study are also provided, allowing for a comprehensive understanding of the effectiveness and applicability of our proposed method. © 2023 IEEE.

关键词： Evolutionary multi-objective optimization algorithms Multi-objective combinatorial optimization Population initialization

Superpixelwise Low-rank Approximation based Partial Label Learning for Hyperspectral Image Classification

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yang, Shujun Zhang, Yu Ding, Yao Hong, Danfeng Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen518055 China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and Engineering Southern University of Science and Technology Peng Cheng Laboratory Shenzhen518055 China School of Optical Engineering Xi'an Research Institute of High Technology Xi’an710025 China Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China

Insufficient prior knowledge of a captured hyperspectral image (HSI) scene may lead the experts or the automatic labeling systems to offer incorrect labels or ambiguous labels (i.e., assigning each training sample to a group of candidate labels, among which only one of them is valid;this is also known as partial label learning) during the labeling process. Accordingly, how to learn from such data with ambiguous labels is a problem of great practical importance. In this paper, we propose a novel superpixelwise low-rank approximation (LRA)- based partial label learning method, namely SLAP, which is the first to take into account partial label learning in HSI classification. SLAP is mainly composed of two phases: disambiguating the training labels and acquiring the predictive model. Specifically, in the first phase, we propose a superpixelwise LRA-based model, preparing the affinity graph for the subsequent label propagation process while extracting the discriminative representation to enhance the following classification task of the second phase. Then to disambiguate the training labels, label propagation propagates the labeling information via the affinity graph of training pixels. In the second phase, we take advantage of the resulting disambiguated training labels and the discriminative representations to enhance the classification performance. The extensive experiments validate the advantage of the proposed SLAP method over state-of-the-art methods. © 2024, CC BY.

关键词： Learning systems

Phase Segmentation of Ni/YSZ Anode for Solid Oxide Fuel Cells by Deep Learning

学校读者我要写书评

暂无评论

Phase Segmentation of Ni/YSZ Anode for Solid Oxide Fuel Cell...

243rd ECS Meeting

作者： Wang, Y. Matsui, Y. Hosomizo, A. Kishimoto, M. Han, M. Iwai, H. Department of Mechanical Engineering and Science Kyoto University Nishikyo-ku Kyoto615-8540 Japan State Key Laboratory of Control and Simulation of Power Systems and Generation Equipment Department of Energy and Power Engineering Tsinghua University Beijing100084 China

ISBN: (纸本)9781607685395

A deep learning network is implemented for the phase segmentation of Ni/YSZ anode of solid oxide fuel cells (SOFCs), as manual segmentation of focused ion beam-scanning electron microscopy (FIB-SEM) images is time-consuming. Segmentation is performed on two samples with different volume ratios of Ni to YSZ. The mean intersection over union (mIoU) reaches 0.9363, indicating good agreement between the predicted images and the manually segmented images. Furthermore, the impact of image augmentation on segmentation accuracy is investigated, and it is found that augmentation is necessary when the number of images in the training set is small or the training and testing sets come from different samples. Furthermore, mixing a sixth of manually segmented images from a new sample into the training set can significantly improve the accuracy of automated segmentation for the new sample. This strategy reduces the number of images requiring manual segmentation and improves processing efficiency. © The Electrochemical Society.

关键词： Solid oxide fuel cells (SOFC)

Development of a Method to Determine the Environmental Burden of Diseases and an Application to Identify Factors Driving Changes in the Number of PM_(2.5)-Related Deaths in China between 2000 and 2010

学校读者我要写书评

暂无评论

Environment & Health 2024年第9期2卷 642-650页

作者： Ning Kang Pengfei Li Tao Xue Tong Zhu Institute of Reproductive and Child Health National Health Commission Key Laboratory of Reproductive Health/Department of Epidemiology and BiostatisticsMinistry of Education Key Laboratory of Epidemiology of Major Diseases(PKU)School of Public HealthPeking University Health Science CenterBeijing 100191China Institute of Medical Technology Peking University Health Science CenterBeijing 100191China Advanced Institute of Information Technology Peking UniversityHangzhou 311215China State Environmental Protection Key Laboratory of Atmospheric Exposure and Health Risk Management and Center for Environment and HealthPeking UniversityBeijing 100871China State Environmental Protection Key Laboratory of Atmospheric Exposure and Health Risk Management and Center for Environment and Health and State Key Joint Laboratory of Environment Simulation and Pollution ControlCollege of Environmental Sciences and EngineeringPeking UniversityBeijing 100871China

The attributable burden is codetermined by the exposure level and nontarget ***,the conventional method of health impact assessment based on preestablished exposure−response functions includes only a few well-known characteristics and thus is insufficient to capture the comprehensive *** aimed to develop a method to fuse health impact assessment with epidemiological analysis and to identify factors driving baseline *** method was applied to identify the factors underlying the change in the number of fine particulate matter(PM_(2.5))related deaths in China between 2000 and *** the study period,the number of PM_(2.5)-related deaths across China's Mainland increased by 0.62(95%CI:0.57,0.69)million,with 0.65(95%CI:0.47,0.91)million,0.55(95%CI:0.39,0.79)million,and 0.11(95%CI:0.06,0.18)million deaths being associated with increased PM_(2.5)exposure,population aging,and growth in population size,***,economic growth,urbanization,improvement of welfare services,and improvement of hospital services resulted in 0.25(95%CI:0.15,0.40)million,0.16(95%CI:0.10,0.27)million,0.16(95%CI:0.09,0.26)million,and 0.09(95%CI:0.05,0.15)million fewer deaths,*** indicated that increased exposure was the major driver of the change in the number of PM_(2.5)-related deaths,and economic growth was the main driver of increased resilience to air pollution.

关键词： health burden decomposition analysis air pollution fine particulate matter premature deaths

Air — Fuel Ratio Control of SI Engine Based on Feedback Linearization

学校读者我要写书评

暂无评论

Air — Fuel Ratio Control of SI Engine Based on Feedback Lin...

Conference on Vehicle Control and Intelligence (CVCI)

作者： Xin Liu Shaolong Sun Xinfang Li Jinwu Gao Department of Control Science and Engineering State Key Laboratory of Automotive Simulation and Control Jilin University Changchun China

Vehicle engines often operate under various operating conditions, and their air fuel ratio (AFR) system has characteristics of nonlinearity, time-varying, and time delay, which can bring difficulties to system modeling and affect the control effect of the air fuel ratio. Therefore, studying control strategies that consider the characteristics of the air fuel ratio system is of great significance. Firstly, the engine air fuel ratio system is modeled, and a feedback linearization control method is used to design an air fuel ratio controller to ensure that the engine’s air fuel ratio is stable at the target value. Finally, the effectiveness of the modeling of the air fuel ratio system and the air fuel ratio controller was verified through experiments.

关键词：

Collaboration and Controversy Among Experts: Rumor Early Detection by Tuning a Comment Generator

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Bing Zhao, Bingrui Li, Ximing Li, Changchun Gao, Wanfu Wang, Shengsheng College of Computer Science and Technology Jilin University Jilin Changchun China Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education Jilin University China

Over the past decade, social media platforms have been key in spreading rumors, leading to significant negative impacts. To counter this, the community has developed various Rumor Detection (RD) algorithms to automatically identify them using user comments as evidence. However, these RD methods often fail in the early stages of rumor propagation when only limited user comments are available, leading the community to focus on a more challenging topic named Rumor Early Detection (RED). Typically, existing RED methods learn from limited semantics in early comments. However, our preliminary experiment reveals that the RED models always perform best when the number of training and test comments is consistently extensive. This inspires us to address the RED issue by generating more human-like comments to support this hypothesis. To implement this idea, we tune a comment generator by simulating expert collaboration and controversy and propose a new RED framework named CameRed. Specifically, we integrate a mixture-of-expert structure into a generative language model and present a novel routing network for expert collaboration. Additionally, we synthesize a knowledgeable dataset and design an adversarial learning strategy to align the style of generated comments with real-world comments. We further integrate generated and original comments with a mutual controversy fusion module. Experimental results show that CameRed outperforms state-of-the-art RED baseline models and generation methods, demonstrating its effectiveness. Copyright © 2025, The Authors. All rights reserved.

关键词： Tweets

Dual-level Mixup for Graph Few-shot Learning with Fewer Tasks

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Liu, Yonghao Li, Mengyu Giunchiglia, Fausto Huang, Lan Li, Ximing Feng, Xiaoyue Guan, Renchu College of Computer Science and Technology Jilin University Changchun China Department of Information Engineering and Computer Science University of Trento Trento Italy Key Laboratory of Symbolic Computation and Knowledge Engineering The Ministry of Education China

Graph neural networks have been demonstrated as a powerful paradigm for effectively learning graph-structured data on the web and mining content from it. Current leading graph models require a large number of labeled samples for training, which unavoidably leads to overfitting in few-shot scenarios. Recent research has sought to alleviate this issue by simultaneously leveraging graph learning and meta-learning paradigms. However, these graph meta-learning models assume the availability of numerous meta-training tasks to learn transferable meta-knowledge. Such assumption may not be feasible in the real world due to the difficulty of constructing tasks and the substantial costs involved. Therefore, we propose a SiMple yet effectIve approach for graph few-shot Learning with fEwer tasks, named SMILE. We introduce a dual-level mixup strategy, encompassing both within-task and across-task mixup, to simultaneously enrich the available nodes and tasks in meta-learning. Moreover, we explicitly leverage the prior information provided by the node degrees in the graph to encode expressive node representations. Theoretically, we demonstrate that SMILE can enhance the model generalization ability. Empirically, SMILE consistently outperforms other competitive models by a large margin across all evaluated datasets with in-domain and cross-domain settings. Our anonymous code can be found here. Copyright © 2025, The Authors. All rights reserved.

关键词： Contrastive Learning