检索结果-内蒙古大学图书馆

Kernel-learning parameter prediction and evaluation in algebraic multigrid method for several PDEs

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Juan Luo, Junyue Zhang, Fangfang Yue, Xiaoqiang 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

This paper explores the application of kernel learning methods for parameter prediction and evaluation in the Algebraic Multigrid Method (AMG), focusing on several Partial Differential Equation (PDE) problems. AMG is an efficient iterative solver for large-scale sparse linear systems, particularly those derived from elliptic and parabolic PDE discretizations. However, its performance heavily relies on numerous parameters, which are often set empirically and are highly sensitive to AMG’s effectiveness. Traditional parameter optimization methods are either computationally expensive or lack theoretical support. To address this, we propose a Gaussian Process Regression (GPR)-based strategy to optimize AMG parameters and introduce evaluation metrics to assess their effectiveness. Trained on small-scale datasets, GPR predicts nearly optimal parameters, bypassing the time-consuming parameter sweeping process. We also use kernel learning techniques to build a kernel function library and determine the optimal kernel function through linear combination, enhancing prediction accuracy. In numerical experiments, we tested typical PDEs such as the constant-coefficient Poisson equation, variable-coefficient Poisson equation, diffusion equation, and Helmholtz equation. Results show that GPR-predicted parameters match grid search results in iteration counts while significantly reducing computational time. A comprehensive analysis using metrics like mean squared error, prediction interval coverage, and Bayesian information criterion confirms GPR’s efficiency and reliability. These findings validate GPR’s effectiveness in AMG parameter optimization and provide theoretical support for AMG’s practical application. © 2025, CC BY.

关键词： Poisson equation

A Tetrahedral Spectral Element Method for Thermo-Mechanical Analysis of Electronic Devices

学校读者我要写书评

暂无评论

IEEE Transactions on Components, Packaging and Manufacturing Technology 2025年

作者： Feng, Naixing Zhang, Shuai Huang, Zhixiang Liu, Qi Qiang Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Information Materials and Intelligent Sensing Laboratory of Anhui Province Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes Hefei China Hangzhou Dianzi University School of Electronics and Information Engineering Hangzhou310018 China

For the coupled thermo-mechanical simulation of complex electronic devices, we propose a Tetrahedral Spectral Element Method (TSEM), which truly combines the high accuracy of spectral methods with the strong geometric adaptability of Finite Element Methods (FEMs). The TSEM employs a collapse transformation method and successfully converts the orthogonal Gauss-Lobatto-Legendre (GLL) basis functions from a hexahedron to a tetrahedral reference element. This ensures numerical accuracy and stability for arbitrary high-order interpolation. We also generate non-equidistant GLL spectral interpolation nodes for tetrahedral elements through Warp&Blend transformation, enabling direct nodal numerical integration calculation through Vandermonde matrices. This approach replaces the classical Gaussian quadrature in the FEM, not only significantly enhancing the computational efficiency of element matrix but also avoiding potential numerical dissipation and dispersion associated with Gaussian integration, thus achieving rapid convergence. In the TSEM thermo-mechanical coupling, we further construct a separate solver based on the implicit Newmark-β method, which realizes unconditional stability for temporal integration for arbitrary time step increment. Moreover, it supports independent inversion of system matrices for temperature and stress fields, without increasing computational resource consumption due to the coupling of multi-physics equations. By quantitatively comparing with the COMSOL Multiphysics software, several typical case studies are used to demonstrate the significant advantages of the TSEM in numerical accuracy, efficiency, and stability. © 2025 IEEE. All rights reserved.

关键词： Orthogonal functions

A Nonconformal SETI-DP Method for Transient Thermal Simulation

学校读者我要写书评

暂无评论

IEEE Transactions on Components, Packaging and Manufacturing Technology 2025年

作者： Feng, Naixing Li, Hongyang Huang, Zhixiang Liu, Qi Qiang Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education The Information Materials and Intelligent Sensing Laboratory of Anhui Province The Key Laboratory of Electromagnetic Environmental Sensing of Anhui Higher Education Institutes Hefei China Hangzhou Dianzi University School of Electronics and Information Engineering Hangzhou310018 China

This paper proposes a novel nonconformal meshbased dual-primal spectral element tearing and interconnecting (SETI-DP) method designed for the efficient transient simulation of complex large-scale heat conduction problems utilizing a domain decomposition method (DDM). This method allows for the division of complex, large-scale problems into smaller subdomain problems. By applying Robin-type transmission conditions at the subdomain interfaces, rapid convergence of the global interface iterative solution is achieved for arbitrary non-conformal subdomain problems. This non-conformal DDM approach supports independent meshing of subdomains, eliminating the need to generate a globally continuous mesh for large-scale problems, thereby significantly enhancing meshing efficiency. In addition, this non-conformal meshing strategy enables high-contrast spatial discretization and mixed-order spectral interpolation between different subdomains. This significantly increases meshing flexibility, minimizes the number of degrees of freedom (DoF) in multi-scale problems, and reduces computational costs. In addition, by developing a subdomain-coupled time iteration scheme, the global corner problem of residual transfer is explicitly given, which greatly improves the versatility and flexibility of the algorithm. Finally, to demonstrate the accuracy, efficiency, and robustness of our algorithm, we conduct benchmark tests on several representative examples. © 2011-2012 IEEE.

关键词： Domain decomposition methods

MaintaAvatar: A Maintainable Avatar Based on Neural Radiance Fields by Continual Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gu, Shengbo Qiu, Yu-Kun Tang, Yu-Ming Wu, Ancong Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Peng Cheng Laboratory Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The generation of a virtual digital avatar is a crucial research topic in the field of computer vision. Many existing works utilize Neural Radiance Fields (NeRF) to address this issue and have achieved impressive results. However, previous works assume the images of the training person are available and fixed while the appearances and poses of a subject could constantly change and increase in real-world scenarios. How to update the human avatar but also maintain the ability to render the old appearance of the person is a practical challenge. One trivial solution is to combine the existing virtual avatar models based on NeRF with continual learning methods. However, there are some critical issues in this approach: learning new appearances and poses can cause the model to forget past information, which in turn leads to a degradation in the rendering quality of past appearances, especially color bleeding issues, and incorrect human body poses. In this work, we propose a maintainable avatar (MaintaAvatar) based on neural radiance fields by continual learning, which resolves the issues by utilizing a Global-Local Joint Storage Module and a Pose Distillation Module. Overall, our model requires only limited data collection to quickly fine-tune the model while avoiding catastrophic forgetting, thus achieving a maintainable virtual avatar. The experimental results validate the effectiveness of our MaintaAvatar model. © 2025, CC BY.

关键词： Federated learning

MBF-DTI: A Fused Multi-dimensional Biochemical Feature-Based Drug Target Prediction Method Based on Heterogeneous Graph Attention Networks 10th

学校读者我要写书评

暂无评论

MBF-DTI: A Fused Multi-dimensional Biochemical Feature-Based...

10th China Health Information Processing Conference, CHIP 2024

作者： Zhao, Haixue Yao, Kui Liu, Yunjiong Che, Chao Tang, Lin Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116622 China School of Software Engineering Dalian University Dalian116622 China

ISBN: (纸本)9789819637515

Drug-target interaction prediction help reduce the cost and time of drug development. However, existing research often overlooks the complexity of biological interactions. To address this issue, this paper proposes a DTI prediction model that integrates multi-dimensional biochemical features. Specifically, the model utilizes a heterogeneous graph attention network to capture the topological relationships among biological entities from diverse data, providing a deep understanding of the interactions among drugs, proteins, diseases, and side effects. A molecular attention Transformer network and a CBiNet module are used to extract the key structural features of drugs and targets. By automatically optimizing the weight distribution between drugs and targets, the model enhances the information transfer during network training, significantly improving model performance. Experimental results on real-world datasets demonstrate that the proposed model outperforms the current state-of-the-art methods in the field. Among the top 50 novel COVID-19 therapeutic drugs predicted by our model, 30 have been supported by clinical trials or scientific literature, further demonstrating the effectiveness of our proposed method in drug repurposing. Experimental data and supplementary materials are available online at: https://***/Eadog/MBF-DTI. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： COVID-19

iManip: Skill-Incremental Learning for Robotic Manipulation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Zexin Cai, Jia-Feng Wu, Xiao-Ming Wei, Yi-Lin Tang, Yu-Ming Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Pengcheng Lab China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

The development of a generalist agent with adaptive multiple manipulation skills has been a long-standing goal in the robotics community. In this paper, we explore a crucial task, skill-incremental learning, in robotic manipulation, which is to endow the robots with the ability to learn new manipulation skills based on the previous learned knowledge without re-training. First, we build a skill-incremental environment based on the RLBench benchmark, and explore how traditional incremental methods perform in this setting. We find that they suffer from severe catastrophic forgetting due to the previous methods on classification overlooking the characteristics of temporality and action complexity in robotic manipulation tasks. Towards this end, we propose an incremental Manipulation framework, termed iManip, to mitigate the above issues. We firstly design a temporal replay strategy to maintain the integrity of old skills when learning new skill. Moreover, we propose the extendable PerceiverIO, consisting of an action prompt with extendable weight to adapt to new action primitives in new skill. Extensive experiments show that our framework performs well in Skill-Incremental Learning. Codes of the skill-incremental environment with our framework will be open-source. Copyright © 2025, The Authors. All rights reserved.

关键词： Robot learning

Quantum simulation of a class of highly-oscillatory transport equations via Schrödingerisation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Gu, Anjiao Jin, Shi School of Mathematical Sciences Shanghai Jiao Tong University Shanghai200240 China Institute of Natural Sciences Shanghai Jiao Tong University Shanghai200240 China Ministry of Education Key Laboratory in Scientific and Engineering Computing Shanghai200240 China

In this paper, we present quantum algorithms for a class of highly-oscillatory transport equations, which arise in semiclassical computation of surface hopping problems and other related non-adiabatic quantum dynamics, based on the Born-Oppenheimer approximation. Our method relies on the classical nonlinear geometric optics method, and the recently developed Schrödingerisation approach for quantum simulation of partial differential equations. The Schrödingerisation technique can transform any linear ordinary and partial differential equations into Hamiltonian systems evolving under unitary dynamics, via a warped phase transformation that maps these equations to one higher dimension. We study possible paths for better recoveries of the solution to the original problem by shifting the bad eigenvalues in the Schrödingerized system. Our method ensures the uniform error estimates independent of the wave length, thus allowing numerical accuracy, in maximum norm, even without numerically resolving the physical oscillations. Various numerical experiments are performed to demonstrate the validity of this approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Eigenvalues and eigenfunctions

Multi-Granular Multimodal Clue Fusion for Meme Understanding

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zheng, Li Fei, Hao Dai, Ting Peng, Zuquan Li, Fei Ma, Huisheng Teng, Chong Ji, Donghong Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China National University of Singapore Singapore Singapore Laboratory for Advanced Computing and Intelligence Engineering Wuxi China North China Institute of Computing Technology Beijing China

With the continuous emergence of various social media platforms frequently used in daily life, the multimodal meme understanding (MMU) task has been garnering increasing attention. MMU aims to explore and comprehend the meanings of memes from various perspectives by performing tasks such as metaphor recognition, sentiment analysis, intention detection, and offensiveness detection. Despite making progress, limitations persist due to the loss of fine-grained metaphorical visual clue and the neglect of multimodal text-image weak correlation. To overcome these limitations, we propose a multi-granular multimodal clue fusion model (MGMCF) to advance MMU. Firstly, we design an object-level semantic mining module to extract object-level image feature clues, achieving fine-grained feature clue extraction and enhancing the model’s ability to capture metaphorical details and semantics. Secondly, we propose a brand-new global-local cross-modal interaction model to address the weak correlation between text and images. This model facilitates effective interaction between global multimodal contextual clues and local unimodal feature clues, strengthening their representations through a bidirectional cross-modal attention mechanism. Finally, we devise a dual-semantic guided training strategy to enhance the model’s understanding and alignment of multimodal representations in the semantic space. Experiments conducted on the widely-used MET-MEME bilingual dataset demonstrate significant improvements over state-of-the-art baselines. Specifically, there is an 8.14% increase in precision for offensiveness detection task, and respective accuracy enhancements of 3.53%, 3.89%, and 3.52% for metaphor recognition, sentiment analysis, and intention detection tasks. These results, underpinned by in-depth analyses, underscore the effectiveness and potential of our approach for advancing MMU. Copyright © 2025, The Authors. All rights reserved.

关键词： Semantics

Audio-Visual Collaborative Learning for Weakly Supervised Video Anomaly Detection

学校读者我要写书评

暂无评论

IEEE Transactions on Multimedia 2025年

作者： Meng, Jingke Tian, Huilin Lin, Ge Hu, Jian-Fang Zheng, Wei-Shi Sun Yat-sen University School of Computer Science and Engineering Guangzhou China Peng Cheng Laboratory Shenzhen518005 China Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen University Ministry of Education China

Weakly supervised anomaly detection is to identify the time window when an anomaly event happened based on the video-level label indicating whether the video contains anomaly event or not. Recent efforts have focused on leveraging multi-modal data, specifically combining visual and audio information, to enhance detection accuracy. While some studies have explored intra-video separation techniques, the primary emphasis remains on distinguishing potentially anomalous events scoring highest from those scoring lowest as normal events. Nevertheless, challenges persist in delineating boundaries between normal and abnormal events, particularly when visual differences are subtle. Our proposed framework, called Audio-Visual Collaborative Learning (AVCL), addresses the challenge of ambiguity in weakly supervised anomaly detection. Our core idea centers around utilizing both audio track variations and the perceptual robustness of visual information to detect and differentiate challenging cases, which composed of two essential modules: the Audio-Visual collaborative Hard cases Separation (AVHS) module and the Multi-modal Mutual Learning (MML) module. The AVHS module aims to address the challenge of discerning visually ambiguous clips in anomaly videos, differentiating between normal and abnormal events. To further improve detection accuracy, we introduce the Multi-modal Mutual Learning (MML) module, and this module enables a process of mutual learning to facilitate the exchange of knowledge and expertise between the single-modal branch and the multi-modal branch. We demonstrate that the proposed approach achieves state-of-the-art detection performance on benchmarks of XD-Violence and CCTV-Fightssub datasets. © 1999-2012 IEEE.

关键词： Self-supervised learning