IEEE transactions on artificial intelligence最新文献_第4页

An Integrated Fusion Framework for Ensemble Learning Leveraging Gradient-Boosting and Fuzzy Rule-Based Models 利用梯度提升和模糊规则模型的集合学习综合融合框架

IEEE transactions on artificial intelligence Pub Date : 2024-07-08 DOI: 10.1109/TAI.2024.3424427

Jinbo Li;Peng Liu;Long Chen;Witold Pedrycz;Weiping Ding

{"title":"An Integrated Fusion Framework for Ensemble Learning Leveraging Gradient-Boosting and Fuzzy Rule-Based Models","authors":"Jinbo Li;Peng Liu;Long Chen;Witold Pedrycz;Weiping Ding","doi":"10.1109/TAI.2024.3424427","DOIUrl":"https://doi.org/10.1109/TAI.2024.3424427","url":null,"abstract":"The integration of different learning paradigms has long been a focus of machine learning research, aimed at overcoming the inherent limitations of individual methods. Fuzzy rule-based models excel in interpretability and have seen widespread application across diverse fields. However, they face challenges such as complex design specifications and scalability issues with large datasets. The fusion of different techniques and strategies, particularly gradient boosting, with fuzzy rule-based models offers a robust solution to these challenges. This article proposes an integrated fusion framework that merges the strengths of both paradigms to enhance model performance and interpretability. At each iteration, a fuzzy rule-based model is constructed and controlled by a dynamic factor to optimize its contribution to the overall ensemble. This control factor serves multiple purposes: it prevents model dominance, encourages diversity, acts as a regularization parameter, and provides a mechanism for dynamic tuning based on model performance, thus mitigating the risk of overfitting. Additionally, the framework incorporates a sample-based correction mechanism that allows for adaptive adjustments based on feedback from a validation set. Experimental results substantiate the efficacy of the presented gradient-boosting framework for fuzzy rule-based models, demonstrating performance enhancement, especially in terms of mitigating overfitting and complexity typically associated with many rules. By leveraging an optimal factor to govern the contribution of each model, the framework improves performance, maintains interpretability, and simplifies the maintenance and update of the models.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5771-5785"},"PeriodicalIF":0.0,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Lightweight Parallel Convolutional Neural Network With SVM Classifier for Satellite Imagery Classification 用于卫星图像分类的轻量级并行卷积神经网络与 SVM 分类器

IEEE transactions on artificial intelligence Pub Date : 2024-07-05 DOI: 10.1109/TAI.2024.3423813

Priyanti Paul Tumpa;Md. Saiful Islam

{"title":"Lightweight Parallel Convolutional Neural Network With SVM Classifier for Satellite Imagery Classification","authors":"Priyanti Paul Tumpa;Md. Saiful Islam","doi":"10.1109/TAI.2024.3423813","DOIUrl":"https://doi.org/10.1109/TAI.2024.3423813","url":null,"abstract":"Satellite image classification is crucial for various applications, driving advancements in convolutional neural networks (CNNs). While CNNs have proven effective, deep models often encounter overfitting issues as the network's depth increases since the model has to learn many parameters. Besides this, traditional CNNs have the inherent difficulty of extracting fine-grained details and broader patterns simultaneously. To overcome these challenges, this article presents a novel approach using a lightweight parallel CNN (LPCNN) architecture with a support vector machine (SVM) classifier to classify satellite images. At first, preprocessing such as resizing and sharpening is used to improve image quality. Each branch within the parallel network is designed for specific resolution characteristics, spanning from low (emphasizing broader patterns) to high (capturing fine-grained details), enabling the simultaneous extraction of a comprehensive set of features without increasing network depth. The LPCNN incorporates a dilation factor to expand the network's receptive field without increasing parameters, and a dropout layer is introduced to mitigate overfitting. SVM is used alongside LPCNN because it is effective at handling high-dimensional features and defining complex decision boundaries, which improves overall classification accuracy. Evaluation of two public datasets (EuroSAT dataset and RSI-CB256 dataset) demonstrates remarkable accuracy rates of 97.91% and 99.8%, surpassing previous state-of-the-art models. Finally, LPCNN, with less than 1 million parameters, outperforms high-parameter models by effectively addressing overfitting issues, showcasing exceptional performance in satellite image classification.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5676-5688"},"PeriodicalIF":0.0,"publicationDate":"2024-07-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Cross-View Masked Model for Self-Supervised Graph Representation Learning 用于自我监督图表示学习的跨视图屏蔽模型

IEEE transactions on artificial intelligence Pub Date : 2024-07-03 DOI: 10.1109/TAI.2024.3419749

Haoran Duan;Beibei Yu;Cheng Xie

{"title":"Cross-View Masked Model for Self-Supervised Graph Representation Learning","authors":"Haoran Duan;Beibei Yu;Cheng Xie","doi":"10.1109/TAI.2024.3419749","DOIUrl":"https://doi.org/10.1109/TAI.2024.3419749","url":null,"abstract":"Graph-structured data plays a foundational role in knowledge representation across various intelligent systems. Self-supervised graph representation learning (SSGRL) has emerged as a key methodology for processing such data efficiently. Recent advances in SSGRL have introduced the masked graph model (MGM), which achieves state-of-the-art performance by masking and reconstructing node features. However, the effectiveness of MGM-based methods heavily relies on the information density of the original node features. Performance deteriorates notably when dealing with sparse node features, such as one-hot and degree-hot encodings, commonly found in social and chemical graphs. To address this challenge, we propose a novel cross-view node feature reconstruction method that circumvents direct reliance on the original node features. Our approach generates four distinct views (graph view, masked view, diffusion view, and masked diffusion view) from the original graph through node masking and diffusion. These views are then encoded into representations with high information density. The reconstruction process operates across these representations, enabling self-supervised learning without direct reliance on the original features. Extensive experiments are conducted on 26 real-world graph datasets, including those with sparse and high information density environments. This cross-view reconstruction method represents a promising direction for effective SSGRL, particularly in scenarios with sparse node feature information.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5540-5552"},"PeriodicalIF":0.0,"publicationDate":"2024-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction 社会 NSTransformers：低质量行人轨迹预测

IEEE transactions on artificial intelligence Pub Date : 2024-07-02 DOI: 10.1109/TAI.2024.3421175

Zihan Jiang;Yiqun Ma;Bingyu Shi;Xin Lu;Jian Xing;Nuno Gonçalves;Bo Jin

{"title":"Social NSTransformers: Low-Quality Pedestrian Trajectory Prediction","authors":"Zihan Jiang;Yiqun Ma;Bingyu Shi;Xin Lu;Jian Xing;Nuno Gonçalves;Bo Jin","doi":"10.1109/TAI.2024.3421175","DOIUrl":"https://doi.org/10.1109/TAI.2024.3421175","url":null,"abstract":"This article introduces a novel model for low-quality pedestrian trajectory prediction, the social nonstationary transformers (NSTransformers), that merges the strengths of NSTransformers and spatiotemporal graph transformer (STAR). The model can capture social interaction cues among pedestrians and integrate features across spatial and temporal dimensions to enhance the precision and resilience of trajectory predictions. We also propose an enhanced loss function that combines diversity loss with logarithmic root mean squared error (log-RMSE) to guarantee the reasonableness and diversity of the generated trajectories. This design adapts well to complex pedestrian interaction scenarios, thereby improving the reliability and accuracy of trajectory prediction. Furthermore, we integrate a generative adversarial network (GAN) to model the randomness inherent in pedestrian trajectories. Compared to the conventional standard Gaussian distribution, our GAN approach better simulates the intricate distribution found in pedestrian trajectories, enhancing the trajectory prediction's diversity and robustness. Experimental results reveal that our model outperforms several state-of-the-art methods. This research opens the avenue for future exploration in low-quality pedestrian trajectory prediction.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5575-5588"},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimal Trajectory-Based Control of 3-D Dual Rotary Cranes for Payload Dynamic Regulation in Complex Environments 基于轨迹的三维双旋转起重机优化控制，实现复杂环境下的有效载荷动态调节

IEEE transactions on artificial intelligence Pub Date : 2024-07-02 DOI: 10.1109/TAI.2024.3421172

Zhuoqing Liu;Tong Yang;Yongchun Fang;Ning Sun

{"title":"Optimal Trajectory-Based Control of 3-D Dual Rotary Cranes for Payload Dynamic Regulation in Complex Environments","authors":"Zhuoqing Liu;Tong Yang;Yongchun Fang;Ning Sun","doi":"10.1109/TAI.2024.3421172","DOIUrl":"https://doi.org/10.1109/TAI.2024.3421172","url":null,"abstract":"With flexible payload adjustment ability and large load capacity, dual rotary cranes (DRCs) provide effective solutions for various complex hoisting tasks. At present, the control research for DRCs mostly focuses on two-dimensional space (restricting workspace and efficiency), or lacks the consideration of DRC dynamic characteristics and the practical demands for the dynamic regulation of payload positions and attitudes, which makes it difficult to handle hoisting tasks in complex environments. To tackle these issues, this article proposes an optimal trajectory-based motion control method for three-dimensional (3-D) DRCs in complex environments, effectively tackling key challenges encountered by DRCs operating in 3-D space. The proposed method achieves dynamic regulation of payload position and attitude by DRCs in 3-D space for the \u0000<italic>first</i>\u0000 time, constraining payload velocity and acceleration within reasonable ranges while avoiding obstacles, which represents an advancement in enhancing the efficiency and safety of 3-D DRC operations in complex environments. Specifically, the coupling relationship between the actuated boom motions and the non-actuated payload motions in 3-D space is mathematically solved, which provides the foundation of indirect payload regulation through boom control. Moreover, by introducing multiple performance indicators during optimization, the proposed method ensures satisfactory payload transient performance while maintaining a safe distance from obstacles. Additionally, by the analysis of steady-state equilibrium conditions and the reasonable passing time allocation of virtual via-points, coordinated boom motions with payload swing suppression are realized, ensuring transportation smoothness. Finally, hardware experiments are conducted considering collision-free payload transportation through reciprocating boom pitch/rotation motions, which verifies the effectiveness and practical performance of the proposed method.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5452-5464"},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

StackAMP: Stacking-Based Ensemble Classifier for Antimicrobial Peptide Identification StackAMP：用于抗菌肽鉴定的基于堆叠的集合分类器

IEEE transactions on artificial intelligence Pub Date : 2024-07-02 DOI: 10.1109/TAI.2024.3421176

Tasmin Karim;Md. Shazzad Hossain Shaon;Md. Mamun Ali;Kawsar Ahmed;Francis M. Bui;Li Chen

{"title":"StackAMP: Stacking-Based Ensemble Classifier for Antimicrobial Peptide Identification","authors":"Tasmin Karim;Md. Shazzad Hossain Shaon;Md. Mamun Ali;Kawsar Ahmed;Francis M. Bui;Li Chen","doi":"10.1109/TAI.2024.3421176","DOIUrl":"https://doi.org/10.1109/TAI.2024.3421176","url":null,"abstract":"Antimicrobial peptides (AMPs) play a vital role in the immune defence systems of various organisms and have garnered significant attention for their potential applications in biotechnology and medicine. There are several approaches to identifying AMPs including clinical isolation and characterization, functional genomics, microbiology techniques, and others. However, these methods are mostly expensive, time-consuming, and require well-equipped labs. To overcome these challenges, machine learning models are a potential solution due to their robustness and high predictive capability with less time and cost. In this study, we explored the efficacy of stacking-based ensemble machine-learning techniques to identify AMPs with higher accuracy and precision. Five distinct feature extraction methods, namely amino acid composition, dipeptide composition, moran autocorrelation, geary autocorrelation, and pseudoamino acid composition, were employed to represent the sequence characteristics of peptides. To build robust predictive models, different traditional machine learning algorithms were applied. Additionally, we developed a novel stacking classifier, aptly named StackAMP, to harness the collective power of these algorithms. Our results demonstrated the exceptional performance of the proposed StackAMP ensemble method in AMP identification, achieving an accuracy of 99.97%, 99.93% specificity, and 100% sensitivity. This high accuracy underscores the effectiveness of our approach, which has promising outcomes for the rapid and accurate identification of AMPs in various biological contexts. This study not only contributes to the growing body of knowledge in the field of AMP recognition but also offers a practical tool with potential applications in drug discovery, biotechnology, and disease prevention.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5666-5675"},"PeriodicalIF":0.0,"publicationDate":"2024-07-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated Bundle Branch Block Detection Using Multivariate Fourier–Bessel Series Expansion-Based Empirical Wavelet Transform 利用基于经验小波变换的多变量傅立叶-贝塞尔序列展开自动检测束支阻滞

IEEE transactions on artificial intelligence Pub Date : 2024-07-01 DOI: 10.1109/TAI.2024.3420259

Sibghatullah Inayatullah Khan;Ram Bilas Pachori

{"title":"Automated Bundle Branch Block Detection Using Multivariate Fourier–Bessel Series Expansion-Based Empirical Wavelet Transform","authors":"Sibghatullah Inayatullah Khan;Ram Bilas Pachori","doi":"10.1109/TAI.2024.3420259","DOIUrl":"https://doi.org/10.1109/TAI.2024.3420259","url":null,"abstract":"Bundle branch block (BBB) refers to cardiac condition that causes a delay in the path of electrical impulses, which makes it difficult for the heart to pump blood efficiently throughout the body. Early diagnosing BBB is important in cases where prior heart anomalies exist. Generally, the 12-lead electrocardiogram (ECG) is used to detect the BBB. To ease the ECG recording procedure, vectorcardiography (VCG) has been proposed with three leads ECG system. Manual diagnosis of BBB using ECG is subjective to the expertise of the doctor. To facilitate the doctors, in the present study, we have proposed a novel framework to automatically detect BBB from VCG signals using multivariate Fourier–Bessel series expansion-based empirical wavelet transform (MVFBSE-EWT). The MVFBSE-EWT is applied over the three channels of VCG signal, which results in the varying number of multivariate Fourier–Bessel intrinsic mode functions (MVFBIMFs). To process further, first six number of MVFBIMFs are selected due to their presence in the entire dataset. Each MVFBIMF is represented in higher dimensional phase space. From each phase space trajectory, fractal dimension (FD) is computed with three scales. The feature space is reduced with metaheuristic feature selection algorithm.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5643-5654"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Collision-Free Grasp Detection From Color and Depth Images 从彩色和深度图像进行无碰撞抓取检测

IEEE transactions on artificial intelligence Pub Date : 2024-07-01 DOI: 10.1109/TAI.2024.3420848

Dinh-Cuong Hoang;Anh-Nhat Nguyen;Chi-Minh Nguyen;An-Binh Phi;Quang-Tri Duong;Khanh-Duong Tran;Viet-Anh Trinh;Van-Duc Tran;Hai-Nam Pham;Phuc-Quan Ngo;Duy-Quang Vu;Thu-Uyen Nguyen;Van-Duc Vu;Duc-Thanh Tran;Van-Thiep Nguyen

{"title":"Collision-Free Grasp Detection From Color and Depth Images","authors":"Dinh-Cuong Hoang;Anh-Nhat Nguyen;Chi-Minh Nguyen;An-Binh Phi;Quang-Tri Duong;Khanh-Duong Tran;Viet-Anh Trinh;Van-Duc Tran;Hai-Nam Pham;Phuc-Quan Ngo;Duy-Quang Vu;Thu-Uyen Nguyen;Van-Duc Vu;Duc-Thanh Tran;Van-Thiep Nguyen","doi":"10.1109/TAI.2024.3420848","DOIUrl":"https://doi.org/10.1109/TAI.2024.3420848","url":null,"abstract":"Efficient and reliable grasp pose generation plays a crucial role in robotic manipulation tasks. The advancement of deep learning techniques applied to point cloud data has led to rapid progress in grasp detection. However, point cloud data has limitations: no appearance information and susceptibility to sensor noise. In contrast, color Red, Green, Blue (RGB) images offer high-resolution and intricate textural details, making them a valuable complement to the 3-D geometry offered by point clouds or depth (D) images. Nevertheless, the effective integration of appearance information to enhance point cloud-based grasp detection remains an open question. In this study, we extend the concepts of VoteGrasp \u0000<xref>[1]</xref>\u0000 and introduce an innovative deep learning approach referred to as VoteGrasp Red, Green, Blue, Depth (RGBD). To build robustness to occlusion, the proposed model generates candidates by casting votes and accumulating evidence for feasible grasp configurations. This methodology revolves around fuzing votes extracted from images and point clouds. To further enhance the collaborative effect of merging appearance and geometry features, we introduce a context learning module. We exploit contextual information by encoding the dependency of objects in the scene into features to boost the performance of grasp generation. The contextual information enables our model to increase the likelihood that the generated grasps are collision-free. The efficacy of our model is verified through comprehensive evaluations on the demanding GraspNet-1Billion dataset, leading to a significant improvement of 9.3 in average precision (AP) over the existing state-of-the-art results. Additionally, we provide extensive analyses through ablation studies to elucidate the contributions of each design decision.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5689-5698"},"PeriodicalIF":0.0,"publicationDate":"2024-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Disentangled Cross-modal Fusion for Event-Guided Image Super-resolution 事件引导图像超分辨率的分离式跨模态融合

IEEE transactions on artificial intelligence Pub Date : 2024-06-28 DOI: 10.1109/TAI.2024.3418376

Minjie Liu;Hongjian Wang;Kuk-Jin Yoon;Lin Wang

{"title":"Disentangled Cross-modal Fusion for Event-Guided Image Super-resolution","authors":"Minjie Liu;Hongjian Wang;Kuk-Jin Yoon;Lin Wang","doi":"10.1109/TAI.2024.3418376","DOIUrl":"https://doi.org/10.1109/TAI.2024.3418376","url":null,"abstract":"Event cameras detect the intensity changes and produce asynchronous events with high dynamic range and no motion blur. Recently, several attempts have been made to superresolve the intensity images guided by events. However, these methods directly fuse the event and image features without distinguishing the modality difference and achieve image superresolution (SR) in multiple steps, leading to error-prone image SR results. Also, they lack quantitative evaluation of real-world data. In this article, we present an \u0000<italic>end-to-end</i>\u0000 framework, called \u0000<italic>event-guided image (EGI)-SR</i>\u0000 to narrow the modality gap and subtly integrate the event and RGB modality features for effective image SR. Specifically, EGI-SR employs three crossmodality encoders (CME) to learn modality-specific and modality-shared features from the stacked events and the intensity image, respectively. As such, EGI-SR can better mitigate the negative impact of modality varieties and reduce the difference in the feature space between the events and the intensity image. Subsequently, a transformer-based decoder is deployed to reconstruct the SR image. Moreover, we collect a real-world dataset, with temporally and spatially aligned events and color image pairs. We conduct extensive experiments on the synthetic and real-world datasets, showing EGI-SR favorably surpassing the existing methods by a large margin.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 10","pages":"5314-5324"},"PeriodicalIF":0.0,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142443093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Novel Incentive Mechanism for Federated Learning Over Wireless Communications 无线通信联合学习的新型激励机制

IEEE transactions on artificial intelligence Pub Date : 2024-06-27 DOI: 10.1109/TAI.2024.3419757

Yong Wang;Yu Zhou;Pei-Qiu Huang

{"title":"A Novel Incentive Mechanism for Federated Learning Over Wireless Communications","authors":"Yong Wang;Yu Zhou;Pei-Qiu Huang","doi":"10.1109/TAI.2024.3419757","DOIUrl":"https://doi.org/10.1109/TAI.2024.3419757","url":null,"abstract":"This article studies a federated learning system over wireless communications, where a parameter server shares a global model trained by distributed devices. Due to limited communication resources, not all devices can participate in the training process. To encourage suitable devices to participate, this article proposes a novel incentive mechanism, where the parameter server assigns rewards to the devices, and the devices make participation decisions to maximize their overall profit based on the obtained rewards and their energy costs. Based on the interaction between the parameter server and the devices, the proposed incentive mechanism is formulated as a bilevel optimization problem (BOP), in which the upper level optimizes reward factors for the parameter server and the lower level makes participation decisions for the devices. Note that each device needs to make an independent participation decision due to limited communication resources and privacy concerns. To solve this BOP, a bilevel optimization approach called BIMFL is proposed. BIMFL adopts multiagent reinforcement learning (MARL) to make independent participation decisions with local information at the lower level, and introduces multiagent meta-reinforcement learning to accelerate the training by incorporating meta-learning into MARL. Moreover, BIMFL utilizes covariance matrix adaptation evolutionary strategy to optimize reward factors at the upper level. The effectiveness of BIMFL is demonstrated on different datasets using multilayer perceptron and convolutional neural networks.","PeriodicalId":73305,"journal":{"name":"IEEE transactions on artificial intelligence","volume":"5 11","pages":"5561-5574"},"PeriodicalIF":0.0,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142600392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0