检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Yongzhe Jia Xuyun Zhang Hongsheng Hu Kim-Kwang Raymond Choo Lianyong Qi Xiaolong Xu Amin Beheshti Wanchun Dou State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University China School of Computing Macquarie University Australia School of Information and Physical Sciences University of Newcastle Australia Department of Information Systems and Cyber Security University of Texas at San Antonio USA College of Computer Science and Technology China University of Petroleum (East China) China School of Computer and Software Nanjing University of Information Science and Technology China

ISBN: (纸本)9798331314385

Federated learning (FL) has emerged as a prominent machine learning paradigm in edge computing environments, enabling edge devices to collaboratively optimize a global model without sharing their private data. However, existing FL frameworks suffer from efficacy deterioration due to the system heterogeneity inherent in edge computing, especially in the presence of domain shifts across local data. In this paper, we propose a heterogeneous FL framework DapperFL, to enhance model performance across multiple domains. In DapperFL, we introduce a dedicated Model Fusion Pruning (MFP) module to produce personalized compact local models for clients to address the system heterogeneity challenges. The MFP module prunes local models with fused knowledge obtained from both local and remaining domains, ensuring robustness to domain shifts. Additionally, we design a Domain Adaptive Regularization (DAR) module to further improve the overall performance of DapperFL. The DAR module employs regularization generated by the pruned model, aiming to learn robust representations across domains. Furthermore, we introduce a specific aggregation algorithm for aggregating heterogeneous local models with tailored architectures and weights. We implement DapperFL on a real-world FL platform with heterogeneous clients. Experimental results on benchmark datasets with multiple domains demonstrate that DapperFL outperforms several state-of-the-art FL frameworks by up to 2.28%, while significantly achieving model volume reductions ranging from 20% to 80%. Our code is available at: https://***/jyzgh/DapperFL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identifying the net information flow direction pattern in mutually coupled non-identical chaotic oscillators

arXiv

引用

arXiv 2025年

作者： Ghosh, Anupam Liang, X. San Manshour, Pouya Paluš, Milan Department of Complex Systems Institute of Computer Science The Czech Academy of Sciences Prague18200 Czech Republic Division of Frontier Research Southern Marine Science and Engineering Guangdong Laboratory Zhuhai519000 China Department of Atmospheric & Oceanic Sciences Fudan University Shanghai200438 China

This paper focuses on a fundamental inquiry in a coupled oscillator model framework. It specifically addresses the direction of net information flow in mutually coupled non-identical chaotic oscillators. Adopting a specific form of conditional mutual information as a model-free and asymmetric index, we establish that if the magnitude of the maximum Lyapunov exponent can be defined as the ‘degree of chaos’ of a given isolated chaotic system, a predominant net information transfer exists from the oscillator exhibiting a higher degree of chaos to the other while they are coupled. We incorporate two distinct categories of coupled ‘non-identical’ oscillators to strengthen our claim. In the first category, both oscillators share identical functional forms, differing solely in one parameter value. We also adopt another measure, the Liang–Kleeman information flow, to support the generality of our results. The functional forms of the interacting oscillators are entirely different in the second category. We further extend our study to the coupled oscillator models, where the interacting oscillators possess different dimensions in phase space. These comprehensive analyses support the broad applicability of our results. © 2025, CC BY-NC-ND.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

Many-Problem Surrogates for Transfer Evolutionary Multiobjective Optimization With Sparse Transfer Stacking

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Li, Hao Wan, Fanggao Gong, Maoguo Qin, A.K. Wu, Yue Xing, Lining Xidian University School of Electronic Engineering Key Laboratory of Collaborative Intelligence Systems Ministry of Education Shaanxi Province Xi'an710071 China Inner Mongolia Normal University School of Electronic Engineering Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi'an China and Academy of Artificial Intelligence College of Mathematics Science Hohhot China Swinburne University of Technology Department of Computing Technologies HawthornVIC3122 Australia Xidian University School of Computer Science and Technology Xi'an710071 China

For expensive multiobjective optimization problems, there exists useful knowledge, e.g., the trained surrogate models, can be transferred to assist the optimization of a target optimization problem, which is termed as multi-problem surrogates. Stacking transfer is able to combine the pretrained source surrogate models and the preliminary target model with a meta-regression algorithm to transfer knowledge from source to target. However, when large-scale source models are involved in the many-problem scenarios, the less correlated sources may hurt the target performance, which is known as negative transfer. In this paper, sparse representation of the coefficients of meta-regression is considered to automatically select the most relevant source models for largely avoiding negative transfer. In the proposed many-problem surrogates, the coefficients of the source and target models are assumed to be sparse under the non-negativity and sum-to-one constraints. Then a sparse transfer stacking model is established with l1-norm of the coefficients. Next, the alternating direction method of multipliers is employed to solve the resulting constrained optimization problem by converting it into several much simpler problems. Most of the previous works assume that the costs for evaluation have no much difference and this assumption rarely holds in the real-world applications. In order to further reduce the total costs, an improved surrogate model with a cost-sensitive measure is designed to estimate the cost and select new solutions for real evaluation based on their estimated fitness, uncertainty and cost. Experimental results on synthetic and practical problems have demonstrated the superiority of the proposed many-problem surrogates. © 1997-2012 IEEE.

关键词： Multiobjective optimization sparse representation surrogate-assisted evolutionary algorithm transfer stacking

来源：评论

学校读者我要写书评

暂无评论

Multi-residual 2D network integrating spatial correlation for whole heart segmentation

引用

computers in Biology and Medicine 2024年 172卷 108261-108261页

作者： Huang, Yan Yang, Jinzhu Sun, Qi Yuan, Yuliang Li, Honghe Hou, Yang Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Liaoning Shenyang China School of Computer Science and Engineering Northeastern University Liaoning Shenyang China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Liaoning Shenyang China Department of Radiology Shengjing Hospital of China Medical University Liaoning Shenyang China

Whole heart segmentation (WHS) has significant clinical value for cardiac anatomy, modeling, and analysis of cardiac function. This study aims to address the WHS accuracy on cardiac CT images, as well as the fast inference speed and low graphics processing unit (GPU) memory consumption required by practical clinical applications. Thus, we propose a multi-residual two-dimensional (2D) network integrating spatial correlation for WHS. The network performs slice-by-slice segmentation on three-dimensional cardiac CT images in a 2D encoder–decoder manner. In the network, a convolutional long short-term memory skip connection module is designed to perform spatial correlation feature extraction on the feature maps at different resolutions extracted by the sub-modules of the pre-trained ResNet-based encoder. Moreover, a decoder based on the multi-residual module is designed to analyze the extracted features from the perspectives of multi-scale and channel attention, thereby accurately delineating the various substructures of the heart. The proposed method is verified on a dataset of the multi-modality WHS challenge, an in-house WHS dataset, and a dataset of the abdominal organ segmentation challenge. The dice, Jaccard, average symmetric surface distance, Hausdorff distance, inference time, and maximum GPU memory of the WHS are 0.914, 0.843, 1.066 mm, 15.778 mm, 9.535 s, and 1905 MB, respectively. The proposed network has high accuracy, fast inference speed, minimal GPU memory consumption, strong robustness, and good generalization. It can be deployed to clinical practical applications for WHS and can be effectively extended and applied to other multi-organ segmentation fields. The source code is publicly available at https://***/nancy1984yan/MultiResNet-SC. © 2024 Elsevier Ltd

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

SFedXL: Semi-Synchronous Federated Learning With Cross-Sharpness and Layer-Freezing

引用

IEEE Internet of Things Journal 2025年第12期12卷 18692-18707页

作者： Zhao, Mingxiong Zhao, Shihao Feng, Chenyuan Yang, Howard H. Niyato, Dusit Quek, Tony Q. S. Yunnan University National Pilot School of Software Kunming650500 China Ministry of Education Engineering Research Center of Integration and Application of Digital Learning Technology Beijing100039 China Ministry of Education Engineering Research Center of Cyberspace Kunming650504 China Yunnan University of Finance and Economics Yunnan Key Laboratory of Service Computing Kunming650221 China EURECOM Sophia Antipolis06410 France Zhejiang University University of Illinois Urbana-Champaign Institute Zhejiang University Haining314400 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore

Federated learning (FL) emerges as a potential solution for enabling multiple terminal devices to collaboratively accomplish computational tasks within an Unmanned Aerial Vehicle (UAV) swarm. However, traditional FL approaches, predicated on synchronous data aggregation, are not feasible for a UAV swarm owing to the inherently variable and dynamic nature of their communication networks compared with terrestrial systems. Furthermore, the data procured by UAVs is often highly heterogeneous, attributable to disparities in deployment environments and device attributes. Considering the distinct flight paths and unique operational conditions encountered by different UAVs, a considerable amount of data remains unlabeled. To tackle the challenges associated with asynchronous operations and the prevalence of unlabeled data, we introduce a novel framework termed Semi-synchronous FL with Cross-Sharpness and Layer-Freezing (SFedXL), tailored for a UAV swarm. In particular, we devise a cross-sharpness model training strategy aimed at optimizing the utilization of both labeled and unlabeled datasets. Additionally, we propose an innovative semi-synchronous model aggregation protocol, complemented by client-specific layer-freezing and client cluster scheduling, designed to expedite the training process. Our simulation results indicate that the proposed algorithm surpasses current FL methods in terms of object recognition accuracy and communication efficiency, albeit with a trade-off of increased local computation latency. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A NOTE ON THE ERROR ANALYSIS OF DATA-DRIVEN CLOSURE MODELS FOR LARGE EDDY SIMULATIONS OF TURBULENCE

arXiv

引用

arXiv 2024年

作者： Chakraborty, Dibyajyoti Barwey, Shivam Zhang, Hong Maulik, Romit Pennsylvania State University School of Information Sciences and Technology University ParkPA16802 United States Transportation and Power Systems Division 240 Argonne National Laboratory LemontIL60439 United States Mathematics and Computer Science Division 240 Argonne National Laboratory LemontIL60439 United States

In this work, we provide a mathematical formulation for error propagation in flow trajectory prediction using data-driven turbulence closure modeling. Under the assumption that the predicted state of a large eddy simulation prediction must be close to that of a subsampled direct numerical simulation, we retrieve an upper bound for the prediction error when utilizing a data-driven closure model. We also demonstrate that this error is significantly affected by the time step size and the Jacobian which play a role in amplifying the initial one-step error made by using the closure. Our analysis also shows that the error propagates exponentially with rollout time and the upper bound of the system Jacobian which is itself influenced by the Jacobian of the closure formulation. These findings could enable the development of new regularization techniques for ML models based on the identified error-bound terms, improving their robustness and reducing error propagation. Copyright © 2024, The Authors. All rights reserved.

关键词： Large eddy simulation

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Analysis of Halo Center in Cosmology 21st

Hierarchical Analysis of Halo Center in Cosmology

引用

21st International Conference on Computational science, ICCS 2021

作者： Di, Zichao [Wendy] Rangel, Esteban Yoo, Shinjae Wild, Stefan M. Mathematics and Computer Science Division Argonne National Laboratory LemontIL60439 United States Argonne Leadership Computing Facility Argonne National Laboratory LemontIL60439 United States Computational Science Initiative Brookhaven National Laboratory UptonNY11973 United States

ISBN: (纸本)9783030779603

Ever-increasing data size raises many challenges for scientific data analysis. Particularly in cosmological N-body simulation, finding the center of a dark matter halo suffers heavily from the large computational cost associated with the large number of particles (up to 20 million). In this work, we exploit the latent structure embed in a halo, and we propose a hierarchical approach to approximate the exact gravitational potential calculation for each particle in order to more efficiently find the halo center. Tests of our method on data from N-body simulations show that in many cases the hierarchical algorithm performs significantly faster than existing methods with a desirable accuracy. © 2021, Springer Nature Switzerland AG.

关键词： Particle size analysis

来源：评论

学校读者我要写书评

暂无评论

Is Dataset Quality Still a Concern in Diagnosis Using Large Foundation Model?

arXiv

引用

arXiv 2024年

作者： Lin, Ziqin Li, Heng Li, Zinan Fu, Huazhu Liu, Jiang Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China Institute of High Performance Computing Agency for Science Technology and Research Singapore Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Recent advancements in pre-trained large foundation models (LFM) have yielded significant breakthroughs across various domains, including natural language processing and computer vision. These models have been particularly impactful in the domain of medical diagnostic tasks. With abundant unlabeled data, an LFM has been developed for fundus images using the Vision Transformer (VIT) and a self-supervised learning framework. This LFM has shown promising performance in fundus disease diagnosis across multiple datasets. On the other hand, deep learning models have long been challenged by dataset quality issues, such as image quality and dataset bias. To investigate the influence of data quality on LFM, we conducted explorations in two fundus diagnosis tasks using datasets of varying quality. Specifically, we explored the following questions: Is LFM more robust to image quality? Is LFM affected by dataset bias? Can fine-tuning techniques alleviate these effects? Our investigation found that LFM exhibits greater resilience to dataset quality issues, including image quality and dataset bias, compared to typical convolutional networks. Furthermore, we discovered that overall fine-tuning is an effective adapter for LFM to mitigate the impact of dataset quality issues. Copyright © 2024, The Authors. All rights reserved.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong The School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China The School of Computing Kent Interdisciplinary Research Centre in Cyber Security University of Kent CanterburyCT2 7NF United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China The Intelligent Transportation Systems Lab Innopolis University Innopolis Russia The School of Computer Science and Technology Xidian University China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. © 2004-2012 IEEE. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Spiking neural networks: Towards bio-inspired multimodal perception in robotics

arXiv

引用

arXiv 2024年

作者： Oikonomou, Katerina Maria Balaska, Vasiliki Tsintotas, Konstantinos A. Mavridis, Christos N. Kansizoglou, Ioannis Gasteratos, Antonios The Department of Production and Management Engineering Laboratory of Robotics and Automation Democritus University of Thrace Xanthi Greece The Department of Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

Spiking neural networks (SNNs) have captured apparent interest over the recent years, stemming from neuroscience and reaching the field of artificial intelligence. However, due to their nature SNNs remain far behind in achieving the exceptional performance of deep neural networks (DNNs). As a result, many scholars are exploring ways to enhance SNNs by using learning techniques from DNNs. While this approach has been proven to achieve considerable improvements in SNN performance, we propose another perspective: enhancing the biological plausibility of the models to leverage the advantages of SNNs fully. Our approach aims to propose a brain-like combination of audio-visual signal processing for recognition tasks, intended to succeed in more bio-plausible human-robot interaction applications. © 2024, CC BY-NC-SA.

关键词： Adversarial machine learning

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：