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

Multitask kernel-learning parameter prediction method for solving time-dependent linear systems

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jiang, Kai Zhang, Juan Zhou, Qi Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

Matrix splitting iteration methods play a vital role in solving large sparse linear systems. Their performance heavily depends on the splitting parameters, however, the approach of selecting optimal splitting parameters has not been well developed. In this paper, we present a multitask kernel-learning parameter prediction method to automatically obtain relatively optimal splitting parameters, which contains simultaneous multiple parameters prediction and a data-driven kernel learning. For solving time-dependent linear systems, including linear differential systems and linear matrix systems, we give a new matrix splitting Kronecker product method, as well as its convergence analysis and preconditioning strategy. Numerical results illustrate our methods can save an enormous amount of time in selecting the relatively optimal splitting parameters compared with the exists methods. Moreover, our iteration method as a preconditioner can effectively accelerate GMRES. As the dimension of systems increases, all the advantages of our approaches becomes significantly. Especially, for solving the differential Sylvester matrix equation, the speedup ratio can reach tens to hundreds of times when the scale of the system is larger than one hundred thousand. Copyright © 2022, The Authors. All rights reserved.

关键词： Linear systems

A Noise Extraction Method for Cryo-EM Single-Particle Denoising

学校读者我要写书评

暂无评论

Journal on Big Data 2022年第1期4卷 61-76页

作者： Huanrong Tang Sihan Wang Jianquan Ouyang Tianming Liu Key Laboratory of Intelligent Computing Information Processing Ministry of EducationSchool of Computer Science and School of Cyberspace ScienceXiangtan UniversityXiangtan411100China Department of Computer Science The University of GeorgiaGeorgia30301USA

Cryo-Electron Microscopy(cryo-EM)has become a powerful method to study the structure and function of biological ***,in clustering tasks based on the projection angle of particles in cryoEM,the noise considerably affects the clustering *** denoising algorithms are ineffective due to the extremely low signal-to-noise ratio(SNR)of cryo-EM images and the complexity of noise *** noise of a single particle greatly influences the orientation estimation of the subsequent clustering task,and the result of the clustering task directly affects the accuracy of the 3D *** this paper,we propose a construction method of cryo-EM denoising dataset that uses U-Net to extract noise blocks from cryoEM images,superimpose the noise block with the projected pure particles to construct our simulated *** we adopt a supervised generative adversarial network(GAN)with perceptual loss to train on our simulated dataset and denoise the real cryo-EM single *** method can solve the problem of poor denoising performance caused by assuming that the noise of the Gaussian distribution does not conform to the noise distribution of cryo-EM,and it can retain the useful information of particles to a great *** compared traditional image filtering methods and the classic deep learning denoising algorithm DnCNN on the simulated and real *** results show that the method based on deep learning has more advantages than traditional image denoising *** is worth mentioning that our method achieves a competitive peak signal to noise ratio(PSNR)and structural similarity(SSIM).Moreover,visualization results,indicate that our method can retain the structure information and orientation information of particles to a greater extent compared with other state-of-the-art image denoising *** means that our denoising task can provide considerable help for subsequent cryo-EM clustering tasks.

关键词： Cryo-EM noise extraction denoising GAN

A MULTI-CATEGORY INVERSE DESIGN NEURAL NETWORK AND ITS APPLICATION TO DIBLOCK COPOLYMERS

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wei, Dan Zhou, Tiejun Huang, Yunqing Jiang, Kai Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

In this work, we design a multi-category inverse design neural network to map ordered periodic structure to physical parameters. The neural network model consists of two parts, a classifier and Structure-Parameter-Mapping (SPM) subnets. The classifier is used to identify structure, and the SPM subnets are used to predict physical parameters for desired structures. We also present an extensible reciprocal-space data augmentation method to guarantee the rotation and translation invariant of periodic structures. We apply the proposed network model and data augmentation method to two-dimensional diblock copolymers based on the Landau-Brazovskii model. Results show that the multi-category inverse design neural network is high accuracy in predicting physical parameters for desired structures. Moreover, the idea of multi-categorization can also be extended to other inverse design *** Codes 68T07, 35R30, 35Q68, 74E15, 03C64 Copyright © 2022, The Authors. All rights reserved.

关键词： Block copolymers

Coherence-Based Distributed Document Representation Learning for Scientific Documents

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tan, Shicheng Zhao, Shu Zhang, Yanping Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui Province 230601 China School of Computer Science and Technology Anhui University Anhui Province Hefei230601 China Information Materials and Intelligent Sensing Laboratory of Anhui Province Anhui Province 230601 China

Distributed document representation is one of the basic problems in natural language processing. Currently distributed document representation methods mainly consider the context information of words or sentences. These methods do not take into account the coherence of the document as a whole, e.g., a relation between the paper title and abstract, headline and description, or adjacent bodies in the document. The coherence shows whether a document is meaningful, both logically and syntactically, especially in scientific documents (papers or patents, etc.). In this paper, we propose a coupled text pair embedding (CTPE) model to learn the representation of scientific documents, which maintains the coherence of the document with coupled text pairs formed by segmenting the document. First, we divide the document into two parts (e.g., title and abstract, etc) which construct a coupled text pair. Then, we adopt negative sampling to construct uncoupled text pairs whose two parts are from different documents. Finally, we train the model to judge whether the text pair is coupled or uncoupled and use the obtained embedding of coupled text pairs as the embedding of documents. We perform experiments on three datasets for one information retrieval task and two recommendation tasks. The experimental results verify the effectiveness of the proposed CTPE model. Copyright © 2022, The Authors. All rights reserved.

关键词： Information retrieval

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized Federated Learning 39

学校读者我要写书评

暂无评论

TRAIL: Trust-Aware Client Scheduling for Semi-Decentralized ...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Hu, Gangqiang Lu, Jianfeng Han, Jianmin Cao, Shuqin Liu, Jing Fu, Hao School of Computer Science and Technology Zhejiang Normal University China School of Computer Science and Technology Wuhan University of Science and Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China

ISBN: (纸本)157735897X

Due to the sensitivity of data, Federated Learning (FL) is employed to enable distributed machine learning while safeguarding data privacy and accommodating the requirements of various devices. However, in the context of semi-decentralized FL, clients’ communication and training states are dynamic. This variability arises from local training fluctuations, heterogeneous data distributions, and intermittent client participation. Most existing studies primarily focus on stable client states, neglecting the dynamic challenges inherent in real-world scenarios. To tackle this issue, we propose a TRust-Aware clIent scheduLing mechanism called TRAIL, which assesses client states and contributions, enhancing model training efficiency through selective client participation. We focus on a semi-decentralized FL framework where edge servers and clients train a shared global model using unreliable intra-cluster model aggregation and inter-cluster model consensus. First, we propose an adaptive hidden semi-Markov model to estimate clients’ communication states and contributions. Next, we address a client-server association optimization problem to minimize global training loss. Using convergence analysis, we propose a greedy client scheduling algorithm. Finally, our experiments conducted on real-world datasets demonstrate that TRAIL outperforms state-of-the-art baselines, achieving an improvement of 8.7% in test accuracy and a reduction of 15.3% in training loss. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

FedCross: Intertemporal Federated Learning Under Evolutionary Games 39

学校读者我要写书评

暂无评论

FedCross: Intertemporal Federated Learning Under Evolutionar...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lu, Jianfeng Zhang, Ying Jia, Riheng Cao, Shuqin Liu, Jing Fu, Hao School of Computer Science and Technology Wuhan University of Science and Technology China Key Laboratory of Social Computing and Cognitive Intelligence (Dalian University of Technology) Ministry of Education China School of Computer Science and Technology Zhejiang Normal University China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan University of Science and Technology China

ISBN: (纸本)157735897X

Federated Learning (FL) mitigates privacy leakage in decentralized machine learning by allowing multiple clients to train collaboratively locally. However, dynamic mobile networks with high mobility, intermittent connectivity, and bandwidth limitation severely hinder model updates to the cloud server. Although previous studies have typically addressed user mobility issue through task reassignment or predictive modeling, frequent migrations may result in high communication overhead. Addressing this challenge involves not only dealing with resource constraints, but also finding ways to mitigate the challenges posed by user migrations. We therefore propose a intertemporal incentive framework, FedCross, which ensures the continuity of FL tasks by migrating interrupted training tasks to feasible mobile devices. FedCross comprises two distinct stages: Specifically, in Stage 1, we address the task allocation problem across regions under resource constraints by employing a multi-objective migration algorithm to quantify the optimal task receivers. Moreover, we adopt evolutionary game theory to capture the dynamic decision-making of users, forecasting the evolution of user proportions across different regions to mitigate frequent migrations. In Stage 2, we utilize a procurement auction mechanism to allocate rewards among base stations, ensuring that those providing high-quality models receive optimal compensation. This approach incentivizes sustained user participation, thereby ensuring the overall feasibility of FedCross. Finally, experimental results validate the theoretical soundness of FedCross and demonstrate its significant reduction in communication overhead. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Federated learning

Multiview Subgraph Neural Networks: Self-Supervised Learning With Scarce Labeled Data

学校读者我要写书评

暂无评论

IEEE Transactions on Neural Networks and Learning Systems 2024年第6期36卷 11548-11561页

作者： Zhenzhong Wang Qingyuan Zeng Wanyu Lin Min Jiang Kay Chen Tan Department of Computing The Hong Kong Polytechnic University Hong Kong SAR China Department of Artificial Intelligence Key Laboratory of Multimedia Trusted Perception and Efficient Computing Ministry of Education of China Key Laboratory of Digital Protection and Intelligent Processing of Intangible Cultural Heritage of Fujian and Taiwan Ministry of Culture and Tourism School of Informatics Xiamen University Xiamen Fujian China Department of Computing Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong SAR China Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong SAR China

While graph neural networks (GNNs) have become the de facto standard for graph-based node classification, they impose a strong assumption on the availability of sufficient labeled samples. This assumption restricts the classification performance of prevailing GNNs on many real-world applications suffering from low-data regimes. Specifically, features extracted from scarce labeled nodes could not provide sufficient supervision for the unlabeled samples, leading to severe overfitting. We point out that leveraging subgraphs to capture long-range dependencies can augment the node representation, thus alleviating the low-data regime. To this end, we present a novel self-supervised learning (SSL) framework, called multiview subgraph neural networks (Muse), for handling the long-range dependencies. In particular, we propose an information theory-based identification mechanism to identify two types of subgraphs from the views of input space and latent space, respectively. The former is to capture the local structure of the graph, while the latter captures the long-range dependencies among nodes. By fusing these two views of subgraphs, the learned representations can preserve the topological properties of the graph at large, including the local structure and long-range dependencies, thus maximizing their expressiveness. Theoretically, we provide the generalization error bound to show the effectiveness of capturing complementary information from multiview subgraphs. Empirically, we show a proof-of-concept of Muse on canonical node classification problems on graph data.

关键词： Manifolds Semantics Feature extraction Laplace equations Data mining Sugar Social networking (online) Skeleton Manifold learning Graph neural networks

The Application of the ADI-FDTD method in the 3D hybrid subgrid technique

学校读者我要写书评

暂无评论

The Application of the ADI-FDTD method in the 3D hybrid subg...

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Ziheng Song Guoda Xie Zhixiang Huang Guilin Hou Pan Pan School of Electronic and Information Engineering Anhui university Hefei China Education of Anhui Province. Anhui Province Key Laboratory of Target Recognition and Feature Extraction (Luan Anhui 237000 China) Ministry of Education. the Key Laboratory of Intelligent Computing and Signal Processing Hefei China Anhui Province Anhui University. Key Laboratory of Electromagnetic Environmental Sensing (Hefei 230601 China) Anhui university Hefei China

A hybrid subgrid scheme based on the conventional finite-difference time-domain (FDTD) schemes are proposed. The alternating-direction-implicit FDTD (ADI-FDTD) is used to calculate electromagnetic fields in fine grid regions subgrids and the FDTD method is applied to the coarse grid regions. Numerical results demonstrate that the drastically reduced computation time and memory can be achieved by using the proposed 3D hybrid algorithm.

关键词： Three-dimensional displays Costs Computational modeling Computational electromagnetics Electromagnetic fields Time-domain analysis Finite difference methods