检索结果-内蒙古大学图书馆

Exploring the Privacy-Accuracy Trade-Off Using Adaptive Gradient Clipping in Federated Learning

IEEE Transactions on Network science and engineering 2025年第3期12卷 2254-2265页

作者： Zhang, Benteng Mao, Yingchi He, Xiaoming Ping, Ping Huang, Huawei Wu, Jie Hohai University College of Computer Science and Software Engineering Nanjing211100 China Nanjing University of Posts and Telecommunications College of Internet of Things Nanjing210003 China Sun Yat-Sen University School of Software Engineering Zhuhai519082 China Temple University Center for Networked Computing PhiladelphiaPA19122 United States

In Differentially Private Federated Learning (DP-FL), gradient clipping can prevent excessive noise from being added to the gradient and ensure that the impact of noise is within a controllable range. However, state-of-the-art methods adopt fixed or imprecise clipping thresholds for gradient clipping, which is not adaptive to the changes in the gradients. This issue can lead to a significant degradation in accuracy while training the global model. To this end, we propose Differential Privacy Federated Adaptive gradient Clipping based on gradient Norm (DP-FedACN). DP-FedACN can calculate the decay rate of the clipping threshold by considering the overall changing trend of the gradient norm. Furthermore, DP-FedACN can accurately adjust the clipping threshold for each training round according to the actual changes in gradient norm, clipping loss, and decay rate. Experimental results demonstrate that DP-FedACN can maintain privacy protection performance similar to that of DP-FedAvg under member inference attacks and model inversion attacks. DP-FedACN significantly outperforms DP-FedAGNC and DP-FedDDC in privacy protection metrics. Additionally, the test accuracy of DP-FedACN is approximately 2.61%, 1.01%, and 1.03% higher than the other three baseline methods, respectively. DP-FedACN can improve the global model training accuracy while ensuring the privacy protection of the model. All experimental results demonstrate that the proposed DP-FedACN can help find a fine-grained privacy-accuracy trade-off in DP-FL. © 2013 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Early Diabetic Retinopathy Cyber-Physical Detection System Using Attention-Guided Deep CNN Fusion

引用

IEEE Transactions on Network science and engineering 2025年第3期12卷 1898-1910页

作者： Hossain, M. Shamim Shorfuzzaman, Mohammad King Saud University Research Chair of Pervasive and Mobile Computing Department of Software Engineering College of Computer and Information Sciences Riyadh12372 Saudi Arabia Taif University Department of Computer Science College of Computers and Information Technology Taif21944 Saudi Arabia

Diabetic retinopathy is the most common and severe eye complication of diabetes, and it can cause vision loss or even blindness due to retina damage. Automatic and faster detection of various DR stages is crucial and can benefit both patients and ophthalmologists. With the ubiquity of measurement devices and growing processing power, cyber-physical characterization is becoming an enabler technology in many disciplines. This paper proposes a cyber-physical system (CPS) framework that will aid clinicians in establishing an early diagnosis of DR. Particularly;we present a component-based CPS architecture to use a deep learning-based predictive model deployed on the cloud for effective DR diagnosis and incorporate medical devices. To this end, a deep learning-based explainable CNN fusion model has been introduced in the proposed framework for automatic screening and interpretation of DR stages using digital fundus images. We extract salient features using various fine-tuned CNN models in conjunction with an attention network, and we use a locally connected layer to calculate the weighted contribution of these networks. We measure the performance of our approach using a public dataset comprising fundus images of five different categories. Experimental results demonstrate the proposed approach's effectiveness for faster and more accurate detection of various DR stages. © 2013 IEEE.

关键词： Biomedical equipment

来源：评论

学校读者我要写书评

暂无评论

Evaluating BERT-based language models for detecting misinformation

引用

Neural Computing and Applications 2025年第16期37卷 9937-9968页

作者： Anggrainingsih, Rini Hassan, Ghulam Mubashar Datta, Amitava Information Technology and Data Science Faculty Sebelas Maret University Ir Sutami 36A Central Java Surakarta57126 Indonesia Computer Science and Software Engineering The University of Western Australia 35 Stirling Highway PerthWA6009 Australia

Online misinformation poses a significant challenge due to its rapid spread and limited supervision. To address this issue, automated rumour detection techniques are essential for countering the negative impact of false information. Previous research primarily focussed on extracting text features, which proved time-consuming and less effective. In this study, we contribute substantially to two domains: rumour detection on Twitter and the evaluation of text embeddings. We thoroughly analyse rumour detection models and compare the quality of text embeddings generated by various fine-tuned BERT-based models. Our findings indicate that our proposed models outperform existing techniques. Notably, when we test these models on combined datasets, we observe significant performance improvements with larger training and testing data sizes. We conclude that carefully considering the dataset, data splitting, and classification techniques is crucial for evaluating solution performance. Additionally, we find that differences in the quality of text embeddings between RoBERTa, BERT, and DistilBERT are insignificant. This challenges existing assumptions and highlights the need for future research to explore these nuances further. © The Author(s) 2025.

关键词： BERT-based models Comparative analysis Rumour detection Text embeddings

来源：评论

学校读者我要写书评

暂无评论

Parkinson’s Disease Detection from Resting State EEG Using Multi-head Graph Structure Learning with Gradient Weighted Graph Attention Explanations 7th

Parkinson’s Disease Detection from Resting State EEG Using...

引用

7th International Workshop on Machine Learning in Clinical Neuroimaging, MLCN 2024, Held in Conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Neves, Christopher Zeng, Yong Xiao, Yiming Department of Computer Science and Software Engineering Concordia University MontrealQC Canada Concordia Institute for Information Systems Engineering Concordia University MontrealQC Canada

ISBN: (纸本)9783031787607

Parkinson’s disease (PD) is a debilitating neurodegenerative disease that has severe impacts on an individual’s quality of life. Compared with structural and functional MRI-based biomarkers for the disease, electroencephalography (EEG) can provide more accessible alternatives for clinical insights. While deep learning (DL) techniques have provided excellent outcomes, many techniques fail to model spatial information and dynamic brain connectivity, and face challenges in robust feature learning, limited data sizes, and poor explainability. To address these issues, we proposed a novel graph neural network (GNN) technique for explainable PD detection using resting state EEG. Specifically, we employ structured global convolutions with contrastive learning to better model complex features with limited data, a novel multi-head graph structure learner to capture the non-Euclidean structure of EEG data, and a head-wise gradient-weighted graph attention explainer to offer neural connectivity insights. We developed and evaluated our method using the UC San Diego Parkinson’s disease EEG dataset, and achieved 69.40% detection accuracy in subject-wise leave-one-out cross-validation while generating intuitive explanations for the learnt graph topology. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Migrant Resettlement by Evolutionary Multiobjective Optimization

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 51-65页

作者： Liu, Dan-Xuan Gu, Yu-Ran Qian, Chao Mu, Xin Tang, Ke Nanjing University National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing210023 China Peng Cheng Laboratory Shenzhen518000 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China

Migration has been a universal phenomenon, which brings opportunities as well as challenges for global development. As the number of migrants (e.g., refugees) increases rapidly, a key challenge faced by each country is the problem of migrant resettlement. This problem has attracted scientific research attention, from the perspective of maximizing the employment rate. Previous works mainly formulated migrant resettlement as an approximately submodular optimization problem subject to multiple matroid constraints and employed the greedy algorithm, whose performance, however, may be limited due to its greedy nature. In this article, we propose a new framework called migrant resettlement by evolutionary multiobjective optimization (MR-EMO), which reformulates migrant resettlement as a biobjective optimization problem that maximizes the expected number of employed migrants and minimizes the number of dispatched migrants simultaneously, and employs a multiobjective evolutionary algorithm (MOEA) to solve the biobjective problem. We implement MR-EMO using three MOEAs: the popular nondominated sorting genetic algorithm II (NSGA-II), MOEA based on decomposition (MOEA/D) as well as the theoretically grounded global simple evolutionary multiobjective optimizer (GSEMO). To further improve the performance of MR-EMO, we propose a specific MOEA, called GSEMO using matrix-swap mutation and repair mechanism (GSEMO-SR), which has a better ability to search for feasible solutions. We prove that MR-EMO using either GSEMO or GSEMO-SR can achieve better theoretical guarantees than the previous greedy algorithm. Experimental results under the interview and coordination migration models clearly show the superiority of MR-EMO (with either NSGA-II, MOEA/D, GSEMO or GSEMO-SR) over previous algorithms, and that using GSEMO-SR leads to the best performance of MR-EMO. © 2024 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Advancing Sentiment Analysis for Low-Resource Languages Using Fine-Tuned LLMs: A Case Study of Customer Reviews in Turkish Language

引用

IEEE Access 2025年 13卷 77382-77394页

作者： Kiziltepe, Rukiye Savran Ezin, Ercan Yentür, Ömer Basbrain, Arwa M. Karakus, Murat Ankara University Department of Software Engineering Ankara06100 Turkey Harran University Department of Computer Engineering Şanlıurfa63200 Turkey Software Solutions-Data Security and Data Management Kron Technology İstanbul34467 Turkey King Abdulaziz University Department of Computer Science Jeddah21589 Saudi Arabia

This study investigates the application of advanced fine-tuned Large Language Models (LLMs) for Turkish Sentiment Analysis (SA), focusing on e-commerce product reviews. Our research utilizes four open-source Turkish SA datasets: Turkish Sentiment Analysis version 1 (TRSAv1), Vitamins and Supplements Customer Review (VSCR), Turkish Sentiment Analysis Dataset (TSAD), and TR Customer Review (TRCR). While these datasets were initially labeled based on star ratings, we implemented a comprehensive relabeling process using state-of-the-art LLMs to enhance data quality. To ensure reliable annotations, we first conducted a comparative analysis of different LLMs using the Cohen’s Kappa agreement metric, which led to the selection of ChatGPT-4o-mini as the best-performing model for dataset annotation. Our methodology then focuses on evaluating the SA capabilities of leading instruction-tuned LLMs through a comparative analysis of zero-shot models and Low-Rank Adaptation (LoRA) fine-tuned LlaMA-3.2-1B-IT and Gemma-2-2B-IT models. Evaluations were conducted on both in-domain and out-domain test sets derived from the original star-ratings-based labels and the newly generated GPT labels. The results demonstrate that our fine-tuned models outperformed leading commercial LLMs by 6% in both in-domain and out-domain evaluations. Notably, models fine-tuned on GPT-generated labels achieved superior performance, with in-domain and out-domain F1-scores reaching 0.912 and 0.9184, respectively. These findings underscore the transformative potential of combining LLM relabeling with LoRA fine-tuning for optimizing SA, demonstrating robust performance across diverse datasets and domains. © 2013 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Local Optimisation Based Detection of Weak Targets in Isolated Forests 24

Local Optimisation Based Detection of Weak Targets in Isolat...

引用

8th International Conference on Electronic Information Technology and computer engineering, EITCE 2024

作者： Hu, Jurong Xing, Yanxiao Li, Yuxiao School of Information Science and Engineering Hohai University Jiangsu Nanjing China School of Computer and Software Hohai University Jiangsu Nanjing China

ISBN: (纸本)9798400710094

Aiming at the problem that the iForest algorithm is not sensitive enough to local anomalies and produces a large number of false alarms in the detection results on some low sea state datasets, this paper proposes the iForest algorithm based on an improved splitting strategy. The algorithm introduces the Gini impurity, incorporates the Gini impurity parameter into the splitting strategy, and is more targeted in the selection of splitting attributes and splitting points, thus better adapting to the problem of detecting weak targets under different sea states, and has an excellent performance of high accuracy, low time duration, and low false alarm rate compared with the traditional methods in anomaly detection. © 2024 Copyright held by the owner/author(s).

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Runtime Verification of Neural-Symbolic Systems 10th

Runtime Verification of Neural-Symbolic Systems

引用

10th International Symposium on Dependable software engineering: Theories, Tools and Applications, SETTA 2024

作者： Deng, Shaojun Liu, Wanwei Zhang, Miaomiao College of Computer Science and Technology National University of Defense Technology Changsha China School of Software Engineering Tongji Uniersity Shanghai China

ISBN: (纸本)9789819606016

Neural-symbolic systems (NSSs), which are typically cyber-physical systems integrated with artificial intelligence modules, have received much attention in both academic and industrial fields. However, thorough verification (such as model checking) of such systems in general leads to prohibitively high costs due to the scale of the state space, and this makes it barely accomplishable within desired time-span. Consequently, light-weight verification techniques are introduced to deal with such cases, e.g., runtime verification (RV, for short). In this paper, we investigate an RV framework for NSSs against signal temporal logic (STL) properties. To guarantee that the on-line monitoring could be accomplished in time, we utilize Euler-prediction to sample the system under scrutiny at discrete time-steps. Our framework supports both qualitative and quantitative on-line monitoring of STL specifications, and thus it terminates whenever a property is satisfied and/or violated by a finite prefix of the trajectory, and it can also provide the bounds of the quantitative satisfaction/violation w.r.t. the remaining execution. Notably, for the so-called piece-wise linear NSSs against affine STL formulas, our approach is exact. On top of it, a prototype tool is implemented, and is experimentally evaluated. The results demonstrate the feasibility of the presented runtime verification approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models 31

VisualRWKV: Exploring Recurrent Neural Networks for Visual L...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Hou, Haowen Zeng, Peigen Ma, Fei Yu, Fei Richard Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shool of Information Technology Carleton University Canada

ISBN: (纸本)9798891761964

Visual Language Models (VLMs) have rapidly progressed with the recent success of large language models. However, there have been few attempts to incorporate efficient linear Recurrent Neural Networks (RNNs) architectures into VLMs. In this study, we introduce VisualRWKV, the first application of a linear RNN model to multimodal learning tasks, leveraging the pre-trained RWKV language model. We propose a data-dependent recurrence and sandwich prompts to enhance our modeling capabilities, along with a 2D image scanning mechanism to enrich the processing of visual sequences. Extensive experiments demonstrate that VisualRWKV achieves competitive performance compared to Transformer-based models like LLaVA-1.5 on various benchmarks. Compared to LLaVA-1.5, VisualRWKV has a speed advantage of 3.98 times and can save 54% of GPU memory when reaching an inference length of 24K tokens. To facilitate further research and analysis, we have made the checkpoints and the associated code publicly accessible at the following GitHub repository: https://***/howard-hou/VisualRWKV. © 2025 Association for Computational Linguistics.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

TunSLR-25: A New Static Tunisian Sign Language Recognition System 41st

TunSLR-25: A New Static Tunisian Sign Language Recognition S...

引用

41st computer Graphics International Conference, CGI 2024

作者： Aloui, Sarra Wang, Yu Fan-fan, Zhou College of Computer Science and Software Engineering Hohai University Nanjing China First Affiliated Hospital of Kunming Medical University Kunming China

ISBN: (纸本)9783031818059

There are 466 M deaf across the world according to World Health Organisation. They are deprived of their basic human right which is communicating with others. Many solutions have been developed to help hard-of-hearing people overcome communication barriers. The existing sign language recognition research focuses on sign languages other than Tunisian Sign Language. Consequently, a Tunisian Sign Language dataset, TunSL-D, was developed for this research. The dataset contains static images that are more complex and can generalize the classification tasks. The images represent the most used words and alphabets in Tunisian Sign language. This paper proposes a novel model TunSLR-25 that recognizes and classifies static Tunisian sign language. The model is first trained on the words data, achieving an accuracy of 95.49%, then trained on both words and alphabets, achieving an accuracy of 88%, with a low parameter number of 1,098,901. The TunSL-D has been trained on SLRNet-8 CNN, a 4-layer CNN model, pre-trained models Resnet50, Resnet101, and InceptionV3. The paper compares the performance of these CNN models and the proposed CNN model TunSLR-25. The system will be integrated into a web application designed to be accessible and user-friendly for this community. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Classification SLR Tunisian Sign Language

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：