检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xia, Shuyin Lian, Xiaoyu Sang, Binbin Wang, Guoyin Gao, Xinbo Chongqing Key Laboratory of Computational Intelligence Key Laboratory of Big Data Intelligent Computing Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China College of Computer and Information Science the National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing401331 China

Fuzzy rough set theory is effective for processing datasets with complex attributes, supported by a solid mathematical foundation and closely linked to kernel methods in machine learning. Attribute reduction algorithms and classifiers based on fuzzy rough set theory exhibit promising performance in the analysis of high-dimensional multivariate complex data. However, most existing models operate at the finest granularity, rendering them inefficient and sensitive to noise, especially for high-dimensional big data. Thus, enhancing the robustness of fuzzy rough set models is crucial for effective feature selection. Muiti-garanularty granular-ball computing, a recent development, uses granular-balls of different sizes to adaptively represent and cover the sample space, performing learning based on these granular-balls. This paper proposes integrating multi-granularity granular-ball computing into fuzzy rough set theory, using granular-balls to replace sample points. The coarse-grained characteristics of granular-balls make the model more robust. Additionally, we propose a new method for generating granular-balls, scalable to the entire supervised method based on granular-ball computing. A forward search algorithm is used to select feature sequences by defining the correlation between features and categories through dependence functions. Experiments demonstrate the proposed model’s effectiveness and superiority over baseline methods. The source codes and datasets are both available on the public link: https://***/lianxiaoyu724/GBFRS Copyright © 2025, The Authors. All rights reserved.

关键词： Granular computing

来源：评论

学校读者我要写书评

暂无评论

Binary-Encoding-Based Quantized Kalman Filter: An Approximate MMSE Approach

引用

IEEE Transactions on Automatic Control 2025年第5期70卷 3181-3196页

作者： Liu, Qinyuan Nie, Yao Wang, Zidong Dong, Hongli Jiang, Changjun Tongji University School of Computer Science and Technology Shanghai201804 China Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China Tongji University Shanghai Artificial Intelligence Laboratory Shanghai201804 China Brunel University London Department of Computer Science UxbridgeUB8 3PH United Kingdom Northeast Petroleum University Artificial Intelligence Energy Research Institute Daqing163318 China Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Daqing163318 China

In this article, the Kalman filter design problem is investigated for linear discrete-time systems under binary encoding schemes. Under such a scheme, the local information is quantized into a bit string by the remote sensor based on a probabilistic quantizer, and then the bit string is transmitted via memoryless binary symmetric channels (BSCs). Due to the communication link noises, the bit flipping occurs in a random manner, and thus, the transmission of the bit string would suffer from specific bit-error rates. With the received bits, a recursive binary-encoding-based quantized Kalman filter is established in the approximate minimum mean-square error (MMSE) sense, which relies on the Gaussian approximation of the conditional probability density function at each iteration. Furthermore, the proposed estimator is shown to be of a Kalman-like type through performance analysis, which exhibits computational complexity comparable to the conventional Kalman filter. Subsequently, a posterior Cramér-Rao lower bound is derived for the proposed binary-encoding-based quantized Kalman filter. The effectiveness of the proposed estimator is demonstrated through numerical results. © 1963-2012 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

MSMAE-Net: multi-semantic and multi-attention enhanced network for image forgery localization

引用

Signal, Image and Video Processing 2025年第7期19卷 1-11页

作者： Liao, Jianjun Su, Lichao Lu, Menghan Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

The popularization of modern digital image technology has brought convenience to us, but it also poses many risks. The advancement of image editing software allows anyone to modify image content effortlessly. If these modified images are abused, they can severely impact societal safety and stability. To address these risks, we propose an end-to-end multi-scale collaborative enhancement image forgery localization network, termed MSMAE-Net. The method first employs a multi-branch feature extractor to initially capture both global and local information, with each branch optimized for different contextual information and features of the image. Next, to enhance the model’s ability to capture forged traces at various levels while maintaining the correlation between different spatial hierarchies, a boundary information aggregation module is designed. By constructing multiple branches with different receptive fields and collaborative learning with each other, a nested collaborative enhancement branch is designed to make the backbone network pay more attention to key features, so as to obtain better feature representation capability. Furthermore, to further fuse different semantic information, a novel strongly compatible semantic attention fusion module is proposed in this paper. Finally, an attention enhancement module is introduced in the localization of forgery regions to adaptively concentrate on key forged areas in the image and effectively capture the relationships between different pixels. In the experiments, we demonstrate that MSMAE-Net exhibits significant advantages in both localization accuracy and robustness in complex forgery scenarios when compared to other SOTA image forgery detection methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy-Aware Task Offloading for Rotatable STAR-RIS-Enhanced Mobile Edge computing Systems

arXiv

引用

arXiv 2025年

作者： Yang, Dongdong Li, Bin Niyato, Dusit School of Computer Science Nanjing University of Information Science and Technology Nanjing210044 China Huzhou Key Laboratory of Urban Multidimensional Perception and Intelligent Computing Huzhou313000 China College of Computing and Data Science Nanyang Technological University Singapore

Simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) can expand the coverage of mobile edge computing (MEC) services by reflecting and transmitting signals simultaneously, enabling full-space coverage. The orientation of the STAR-RIS plays a crucial role in optimizing the gain of received and transmitted signals, and a rotatable STAR-RIS offers potential enhancement for MEC systems. This paper investigates a rotatable STAR-RIS-assisted MEC system, operated under three protocols, namely energy splitting, mode switching, and time switching. The goal is to minimize energy consumption for multiple moving user devices through the joint optimization of STAR-RIS configurations, orientation, computation resource allocation, transmission power, and task offloading strategies. Considering the mobility of user devices, we model the original optimization problem as a sequential decision-making process across multiple time slots. The high-dimensional, highly coupled, and nonlinear nature makes it a challenging non-convex decision-making problem for traditional optimization algorithms. Therefore, a deep reinforcement learning (DRL) approach is employed, specifically utilizing soft actor-critic algorithm to train the DRL model. Simulation results demonstrate that the proposed algorithm outperforms the benchmarks in both convergence speed and energy efficiency, while reducing energy consumption by up to 52.7% compared to the fixed STAR-RIS scheme. Among three operating protocols, the energy splitting yields the best performance. © 2025, CC BY.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Federated Hybrid-Supervised Learning for Universal Medical Image Segmentation

Federated Hybrid-Supervised Learning for Universal Medical I...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zheng, Shenhai Wen, Sian Li, Congyu Chen, Qing Li, Laquan College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing China School of Science Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9798350368741

Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL faces difficulties with heterogeneous data and limited annotations in medical image segmentation. Motivated by this discovery, this study proposes a novel hybrid-supervised federated learning method (FedSLAG) that explores various types of annotations in medical imaging. To focus more on weakly-supervised and unsupervised scenarios within hybrid-supervised learning, a federated Gaussian enhancement module was proposed for heterogeneous sparse annotations (points and scribbles). The feature extraction module combines the features of multiple weakly-supervised clients and establishes the correlation of similar pixels, thus making up for the deficiency of scarce annotations and the insufficient feature extraction capability of a single machine. Then, a two-stage broadcast mechanism based on supervision sparsity was proposed to alleviate optimization deviation in local models. Experiments on breast tumor and skin lesion segmentation tasks demonstrate significant efficiency gains as well as highly competitive segmentation accuracy in many hybrid-supervised situations. Our codes are available at: https://***/TrivenDev/FedSLAG. © 2025 IEEE.

关键词： federated learning hybrid-supervised learning medical image segmentation

来源：评论

学校读者我要写书评

暂无评论

Learned distributed image compression with decoder side information

引用

Digital Communications and Networks 2025年第2期11卷 349-358页

作者： Yin, Yankai Sun, Zhe Ruan, Peiying Li, Ruidong Duan, Feng Tianjin Key Laboratory of Interventional Brain-Computer Interface and Intelligent Rehabilitation Nankai University Tianjin300350 China Institute of Natural Sciences Kanazawa University Ishikawa9201164 Japan Faculty of Health Data Science and Graduate School of Medicine Juntendo University Chiba2790013 Japan NVIDIA AI Technology Center NVIDIA Japan Tokyo1070052 Japan

With the rapid development of digital communication and the widespread use of the Internet of Things, multi-view image compression has attracted increasing attention as a fundamental technology for image data communication. Multi-view image compression aims to improve compression efficiency by leveraging correlations between images. However, the requirement of synchronization and inter-image communication at the encoder side poses significant challenges, especially for constrained devices. In this study, we introduce a novel distributed image compression model based on the attention mechanism to address the challenges associated with the availability of side information only during decoding. Our model integrates an encoder network, a quantization module, and a decoder network, to ensure both high compression performance and high-quality image reconstruction. The encoder uses a deep Convolutional Neural Network (CNN) to extract high-level features from the input image, which then pass through the quantization module for further compression before undergoing lossless entropy coding. The decoder of our model consists of three main components that allow us to fully exploit the information within and between images on the decoder side. Specifically, we first introduce a channel-spatial attention module to capture and refine information within individual image feature maps. Second, we employ a semi-coupled convolution module to extract both shared and specific information in images. Finally, a cross-attention module is employed to fuse mutual information extracted from side information. The effectiveness of our model is validated on various datasets, including KITTI Stereo and Cityscapes. The results highlight the superior compression capabilities of our method, surpassing state-of-the-art techniques. © 2024 Chongqing University of Posts and Telecommunications

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

HybridFL: Hybrid Approach Toward Privacy-Preserving Federated Learning 6th

HybridFL: Hybrid Approach Toward Privacy-Preserving Federate...

引用

6th International Conference on Security and Privacy in New computing Environments, SPNCE 2023

作者： Ali, Sheraz Mamoon, Saqib Usman, Areeba Abidin, Zain ul Zhao, Chuan School of Information Science and Engineering University of Jinan Jinan250022 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China University of Sargodha Sargodha Pakistan Shandong Provincial Key Laboratory of Network-Based Intelligent Computing University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Software Engineering University of Jinan Jinan250022 China

ISBN: (纸本)9783031736988

In this study, we introduce a novel Hybrid Federated Learning (HybridFL) approach aimed at enhancing privacy and accuracy in collaborative machine learning scenarios. Our methodology integrates Differential Privacy (DP) and secret sharing techniques to address inference risks during training and protect against information leakage in the output model. Drawing inspiration from recent advances, we present a HybridFL framework that combines the strengths of Homomorphic Encryption (HE) and Multi-Party Computation (MPC) to achieve secure computation without the computational overhead of pure HE methods. Our contributions include a privacy-preserving design for Federated Learning (FL) that ensures local data privacy through secret sharing while leveraging DP mechanisms for noise addition. The system offers resilience against unreliable participants and is evaluated using various machine learning models, including Convolutional Neural Networks (CNN), Multi-Layer Perceptrons (MLP), and linear regression. Furthermore, we address potential external threats by deploying predictive model outputs as robust services against inference attacks. Experimental results demonstrate improved accuracy and convergence speed, establishing the viability of HybridFL as an effective solution for collaborative machine learning with enhanced privacy guarantees. © ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A contrastive learning framework of graph reconstruction and hypergraph learning for key node identification

引用

Chaos, Solitons and Fractals 2025年 197卷

作者： Huang, Xu-Dong Zhang, Xian-Jie Zhang, Hai-Feng Data Intelligence Lab Research Center For Data To Cyberspace School of Cyber Science and Technology University of Science and Technology of China Hefei Anhui230026 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Mathematical Science Anhui University Hefei Anhui230601 China

With the emergence of complex networks in various domains, the key node identification has become one of the critical issues that needs to be studied. Traditional index methods typically focus on single structural information, while existing data-driven approaches often rely solely on the intrinsic lower-order features of nodes. However, assessing the importance of nodes requires a comprehensive consideration of both network structures and higher-order features from multiple perspectives. To address these challenges, this paper proposes a novel deep learning framework based on Graph Reconstruction and Hypergraph Contrastive Learning, termed GRHCL. The GRHCL method constructs hypergraph structures from original graphs using random walks, followed by leveraging graph reconstruction and hypergraph learning methods to capture both structural and higher-order embedding features of nodes. Positive and negative node pairs are then constructed across different views for contrastive learning. Finally, the model is trained using a training sample set obtained through a clustering sampling strategy, along with a joint loss function. Comparative experiments against various baseline methods demonstrate that the GRHCL method achieves superior predictive performance with smaller training sets, improving accuracy by over 5% on some datasets compared to the next best-performing method. © 2025 Elsevier Ltd

关键词： Clustering sampling Contrastive learning Graph reconstruction learning Hypergraph learning key node identification

来源：评论

学校读者我要写书评

暂无评论

LeapGNN: accelerating distributed GNN training leveraging feature-centric model migration 25

LeapGNN: accelerating distributed GNN training leveraging fe...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Weijian Chen Shuibing He Haoyang Qu Xuechen Zhang The State Key Laboratory of Blockchain and Data Security Zhejiang University and Zhejiang Lab and Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security and Zhejiang Key Laboratory of Big Data Intelligent Computing Washington State University Vancouver

ISBN: (纸本)9781939133458

Distributed training of graph neural networks (GNNs) has become a crucial technique for processing large graphs. Prevalent GNN frameworks are model-centric, necessitating the transfer of massive graph vertex features to GNN models, which leads to a significant communication bottleneck. Recognizing that the model size is often significantly smaller than the feature size, we propose LeapGNN, a feature-centric framework that reverses this paradigm by bringing GNN models to vertex features. To make it truly effective, we first propose a micrograph-based training strategy that leverages a refined structure to enhance locality, combined with the model migration technique, to minimize remote feature retrieval. Then, we devise a feature pre-gathering approach that merges multiple fetch operations into a single one to eliminate redundant feature transmissions. Finally, we employ a micrograph-based merging method that adjusts the number of micrographs for each worker to minimize kernel switches and synchronization overhead. Our experimental results demonstrate that LeapGNN achieves a performance speedup of up to 4.2× compared to the state-of-the-art method, namely P3.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models

arXiv

引用

arXiv 2025年

作者： He, Yu Li, Boheng Liu, Liu Ba, Zhongjie Dong, Wei Li, Yiming Qin, Zhan Ren, Kui Chen, Chun The State Key Laboratory of Blockchain and Data Security Zhejiang University China College of Computing and Data Science Nanyang Technological University Singapore

Membership Inference Attacks (MIAs) aim to predict whether a data sample belongs to the model’s training set or not. Although prior research has extensively explored MIAs in Large Language Models (LLMs), they typically require accessing to complete output logits (i.e., logits-based attacks), which are usually not available in practice. In this paper, we study the vulnerability of pre-trained LLMs to MIAs in the label-only setting, where the adversary can only access generated tokens (text). We first reveal that existing label-only MIAs have minor effects in attacking pre-trained LLMs, although they are highly effective in inferring fine-tuning datasets used for personalized LLMs. We find that their failure stems from two main reasons, including better generalization and overly coarse perturbation. Specifically, due to the extensive pretraining corpora and exposing each sample only a few times, LLMs exhibit minimal robustness differences between members and non-members. This makes token-level perturbations too coarse to capture such differences. To alleviate these problems, we propose PETAL: a label-only membership inference attack based on PEr-Token semAntic simiLarity. Specifically, PETAL leverages token-level semantic similarity to approximate output probabilities and subsequently calculate the perplexity. It finally exposes membership based on the common assumption that members are ‘better’ memorized and have smaller perplexity. We conduct extensive experiments on the WikiMIA benchmark and the more challenging MIMIR benchmark. Empirically, our PETAL performs better than the extensions of existing label-only attacks against personalized LLMs and even on par with other advanced logit-based attacks across all metrics on five prevalent open-source LLMs1. Our study highlights that pre-trained LLMs remain vulnerable to privacy risks posed by MIAs even in the most challenging and realistic setting, calling for attention to develop more effective defenses. Copyright © 20

关键词： Semantics

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：