IEEE Transactions on Emerging Topics in Computational Intelligence最新文献_第9页

Surrogate-Assisted Evolutionary Multi-Objective Optimization of Medium-Scale Problems by Random Grouping and Sparse Gaussian Modeling 通过随机分组和稀疏高斯建模实现中等规模问题的代理辅助多目标进化优化

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-25 DOI: 10.1109/TETCI.2024.3372378

Haofeng Wu;Yaochu Jin;Kailai Gao;Jinliang Ding;Ran Cheng

{"title":"Surrogate-Assisted Evolutionary Multi-Objective Optimization of Medium-Scale Problems by Random Grouping and Sparse Gaussian Modeling","authors":"Haofeng Wu;Yaochu Jin;Kailai Gao;Jinliang Ding;Ran Cheng","doi":"10.1109/TETCI.2024.3372378","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3372378","url":null,"abstract":"Gaussian processes (GPs) are widely employed in surrogate-assisted evolutionary algorithms (SAEAs) because they can estimate the level of uncertainty in their predictions. However, the computational complexity of GPs grows cubically with the number of training samples, the time required for constructing a GP becomes excessively long. Additionally, in SAEAs, the GP is updated using the new data sampled in each round, which significantly impairs its efficiency in addressing medium-scale optimization problems. This issue is exacerbated in multi-objective scenarios where multiple GP models are needed. To address this challenge, we propose a fast SAEA using sparse GPs for medium-scale expensive multi-objective optimization problems. We construct a sparse GP for each objective on randomly selected sub-decision spaces and optimize a multi-objective acquisition function using a multi-objective evolutionary algorithm. The resulting population is combined with the previously evaluated solutions, and k-means is used for clustering to obtain candidate solutions. Before real function evaluations, the candidate solutions in the subspace are completed with the values of the knee point in the archive. Experimental results on three benchmark test suites up to 80 decision variables demonstrate the algorithm's computational efficiency and competitive performance compared to state-of-the-art methods. Additionally, we verify its performance on a real-world optimization problem.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"8 5","pages":"3263-3278"},"PeriodicalIF":5.3,"publicationDate":"2024-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142368452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IEEE Transactions on Emerging Topics in Computational Intelligence Information for Authors 电气和电子工程师学会《计算智能新课题论文集》（IEEE Transactions on Emerging Topics in Computational Intelligence）给作者的信息

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-24 DOI: 10.1109/TETCI.2024.3398387

引用次数: 0

IEEE Computational Intelligence Society Information 电气和电子工程师学会计算智能学会信息

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-24 DOI: 10.1109/TETCI.2024.3398385

引用次数: 0

IEEE Transactions on Emerging Topics in Computational Intelligence Publication Information 电气和电子工程师学会《计算智能新课题论文集》出版信息

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-24 DOI: 10.1109/TETCI.2024.3398383

引用次数: 0

Path Planning for Unmanned Aerial Vehicle via Off-Policy Reinforcement Learning With Enhanced Exploration 通过增强探索的非策略强化学习实现无人飞行器的路径规划

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-22 DOI: 10.1109/TETCI.2024.3369485

Zhengjun Wang;Weifeng Gao;Genghui Li;Zhenkun Wang;Maoguo Gong

{"title":"Path Planning for Unmanned Aerial Vehicle via Off-Policy Reinforcement Learning With Enhanced Exploration","authors":"Zhengjun Wang;Weifeng Gao;Genghui Li;Zhenkun Wang;Maoguo Gong","doi":"10.1109/TETCI.2024.3369485","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3369485","url":null,"abstract":"Unmanned aerial vehicles (UAVs) are widely used in urban search and rescue, where path planning plays a critical role. This paper proposes an approach using off-policy reinforcement learning (RL) with an improved exploration mechanism (IEM) based on prioritized experience replay (PER) and curiosity-driven exploration to address the time-constrained path planning problem for UAVs operating in complex unknown environments. Firstly, to meet the task's time constraints, we design a rollout algorithm based on PER to optimize the behavior policy and enhance sampling efficiency. Additionally, we address the issue that certain off-policy RL algorithms often get trapped in local optima in environments with sparse rewards by measuring curiosity using the states' unvisited time and generating intrinsic rewards to encourage exploration. Lastly, we introduce IEM into the sampling stage of various off-policy RL algorithms. Simulation experiments demonstrate that, compared to the original off-policy RL algorithms, the algorithms incorporating IEM can reduce the planning time required for rescuing paths and achieve the goal of rescuing all trapped individuals.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"8 3","pages":"2625-2639"},"PeriodicalIF":5.3,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141096326","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-Relation Augmentation for Graph Neural Networks 图神经网络的多关系增强

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-21 DOI: 10.1109/TETCI.2024.3371214

Shunxin Xiao;Huibin Lin;Jianwen Wang;Xiaolong Qin;Shiping Wang

{"title":"Multi-Relation Augmentation for Graph Neural Networks","authors":"Shunxin Xiao;Huibin Lin;Jianwen Wang;Xiaolong Qin;Shiping Wang","doi":"10.1109/TETCI.2024.3371214","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3371214","url":null,"abstract":"Data augmentation has been successfully utilized to refine the generalization capability and performance of learning algorithms in image and text analysis. With the rising focus on graph neural networks, an increasing number of researchers are employing various data augmentation approaches to improve graph learning techniques. Although significant improvements have been made, most of them are implemented by manipulating nodes or edges to generate modified graphs as augmented views, which might lose the information hidden in the input data. To address this issue, we propose a simple but effective data augmentation framework termed multi-relation augmentation designed for existing graph neural networks. Different from prior works, the designed model utilizes various methods to simulate multiple adjacency relationships (multi-relation) among nodes as augmented views instead of manipulating the original graph. The proposed augmentation framework can be formulated as three sub-modules, each offering distinct advantages: 1) The encoder module and projection module form a shared contrastive learning framework for both the original graph and all augmented views. Due to the shared mechanism, the proposed method can be simply applied to various graph learning models. 2) The designed task-specific module flexibly extends the proposed framework for various machine learning tasks. Experimental results on several databases show that the introduced augmentation framework improves the performance of existing graph neural networks on both semi-supervised node classification and unsupervised clustering tasks. It demonstrates that multiple relations mechanism is efficient for graph-based augmentation.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"8 5","pages":"3614-3627"},"PeriodicalIF":5.3,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142376910","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Target-Embedding Autoencoder With Knowledge Distillation for Multi-Label Classification 针对多标签分类的目标嵌入式自动编码器与知识蒸馏器

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-21 DOI: 10.1109/TETCI.2024.3372693

Ying Ma;Xiaoyan Zou;Qizheng Pan;Ming Yan;Guoqi Li

{"title":"Target-Embedding Autoencoder With Knowledge Distillation for Multi-Label Classification","authors":"Ying Ma;Xiaoyan Zou;Qizheng Pan;Ming Yan;Guoqi Li","doi":"10.1109/TETCI.2024.3372693","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3372693","url":null,"abstract":"In the task of multi-label classification, it is a key challenge to determine the correlation between labels. One solution to this is the Target Embedding Autoencoder (TEA), but most TEA-based frameworks have numerous parameters, large models, and high complexity, which makes it difficult to deal with the problem of large-scale learning. To address this issue, we provide a Target Embedding Autoencoder framework based on Knowledge Distillation (KD-TEA) that compresses a Teacher model with large parameters into a small Student model through knowledge distillation. Specifically, KD-TEA transfers the dark knowledge learned from the Teacher model to the Student model. The dark knowledge can provide effective regularization to alleviate the over-fitting problem in the training process, thereby enhancing the generalization ability of the Student model, and better completing the multi-label task. In order to make the Student model learn the knowledge of the Teacher model directly, we improve the distillation loss: KD-TEA uses MSE loss instead of KL divergence loss to improve the performance of the model in multi-label tasks. Experiments on multiple datasets show that our KD-TEA framework is superior to the most advanced multi-label classification methods in both performance and efficiency.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"8 3","pages":"2506-2517"},"PeriodicalIF":5.3,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141096306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Differentiable Architecture Search With Attention Mechanisms for Generative Adversarial Networks 针对生成式对抗网络的带有注意机制的可变架构搜索

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-21 DOI: 10.1109/TETCI.2024.3369998

Yu Xue;Kun Chen;Ferrante Neri

{"title":"Differentiable Architecture Search With Attention Mechanisms for Generative Adversarial Networks","authors":"Yu Xue;Kun Chen;Ferrante Neri","doi":"10.1109/TETCI.2024.3369998","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3369998","url":null,"abstract":"Generative adversarial networks (GANs) are machine learning algorithms that can efficiently generate data such as images. Although GANs are very popular, their training usually lacks stability, with the generator and discriminator networks failing to converge during the training process. To address this problem and improve the stability of GANs, in this paper, we automate the design of stable GANs architectures through a novel approach: differentiable architecture search with attention mechanisms for generative adversarial networks (\u0000<bold>DAMGAN\u0000). We construct a generator supernet and search for the optimal generator network within it. We propose incorporating two attention mechanisms between each pair of nodes in the supernet. The first attention mechanism, down attention, selects the optimal candidate operation of each edge in the supernet, while the second attention mechanism, up attention, improves the training stability of the supernet and limits the computational cost of the search by selecting the most important feature maps for the following candidate operations. Experimental results show that the architectures searched by our method obtain a state-of-the-art inception score (IS) of 8.99 and a very competitive Fréchet inception distance (FID) of 10.27 on the CIFAR-10 dataset. Competitive results were also obtained on the STL-10 dataset (IS = 10.35, FID = 22.18). Notably, our search time was only 0.09 GPU days.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"8 4","pages":"3141-3151"},"PeriodicalIF":5.3,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141964788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Probabilistic Nuclear-Norm Matrix Regression Regularized by Random Graph Theory 随机图论规范化的概率核正态矩阵回归

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-21 DOI: 10.1109/TETCI.2024.3372406

Jianhang Zhou;Shuyi Li;Shaoning Zeng;Bob Zhang

{"title":"Probabilistic Nuclear-Norm Matrix Regression Regularized by Random Graph Theory","authors":"Jianhang Zhou;Shuyi Li;Shaoning Zeng;Bob Zhang","doi":"10.1109/TETCI.2024.3372406","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3372406","url":null,"abstract":"The structural information is critical in image analysis as one of the most popular topics in the computational intelligence area. To capture the structural information of the given images, the nuclear-norm matrix regression (NMR) framework provides a natural way by successfully formulating the two-dimensional image error matrix into the image analysis. Nevertheless, although NMR shows its powerful performance in robust face recognition, its intrinsic regression/classification mechanism is still unclear, which restricts its capability. Furthermore, since NMR works in a sample-dependent scheme, it requires remodelling for each given image sample and leads to a failure in learning the intrinsic and structural information from the given image samples. Leveraging the superiority and drawbacks of the NMR framework, in this paper, we propose \u0000<bold>P\u0000robabilistic \u0000<bold>N\u0000uclear-norm \u0000<bold>M\u0000atrix \u0000<bold>R\u0000egression (PNMR). We form the idea of PNMR with theoretical deduction using Bayesian inference to clearly show its probability interpretation, where we present a unified as well as a delicated formulation for optimization. PNMR can be proven to achieve the joint learning of the NMR-style formulation regularized by the \u0000<inline-formula><tex-math>$L_{2,1}$</tex-math></inline-formula>\u0000-norm, making it adaptive to arbitrary given image samples. To fully consider the intrinsic relationships of the observed samples, we propose the \u0000<bold>P\u0000robabilistic \u0000<bold>N\u0000uclear-norm \u0000<bold>M\u0000atrix \u0000<bold>R\u0000egression regularized by \u0000<bold>R\u0000andom \u0000<bold>G\u0000raph (PNMR-RG) on the basis of PNMR. Extensive experiments on several image datasets were performed and comparisons were made with 10 state-of-the-art methods to demonstrate the feasibility and promising performance of both PNMR and PNMR-RG.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"8 4","pages":"2762-2774"},"PeriodicalIF":5.3,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141965839","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Point Cloud Completion via Relative Point Position Encoding and Regional Attention 通过相对点位置编码和区域注意力实现点云补全

IF 5.3 3区计算机科学

IEEE Transactions on Emerging Topics in Computational Intelligence Pub Date : 2024-03-21 DOI: 10.1109/TETCI.2024.3375614

Jiazhong Chen;Furui Liu;Dakai Ren;Lu Guo;Ziyi Liu

{"title":"Point Cloud Completion via Relative Point Position Encoding and Regional Attention","authors":"Jiazhong Chen;Furui Liu;Dakai Ren;Lu Guo;Ziyi Liu","doi":"10.1109/TETCI.2024.3375614","DOIUrl":"https://doi.org/10.1109/TETCI.2024.3375614","url":null,"abstract":"The global feature encoding and surface detail refinement are two critical components for point-based point cloud completion methods. However, existing methods typically use max pooling to hard integrate the neighbouring features, resulting in that the global feature can not well encode the majority of point position information. Moreover, as the important factor of refinement, the position displacement is not well represented and suffers from the information loss of structure details on local and non-local regions. Thus we propose a novel regional attention-based Siamese auto-encoder network architecture, by which the majority of relative point position information is well encoded in the global feature. Then a low order local attention and a high order non-local attention are presented to search the contributive local and non-local features for regressing the position displacements of shape surface. Quantitative and qualitative experiments on PCN, Completion3D, MVP, ShapeNet-55/34, and KITTI datasets show that the proposed method achieves competitive results compared with existing state-of-the-art completion methods.","PeriodicalId":13135,"journal":{"name":"IEEE Transactions on Emerging Topics in Computational Intelligence","volume":"8 6","pages":"3807-3820"},"PeriodicalIF":5.3,"publicationDate":"2024-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142691693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0