IEEE transactions on neural networks and learning systems最新文献

{"title":"Domain Information Mining and State-Guided Adaptation Network for Multispectral Image Segmentation.","authors":"Boyu Zhao,Mengmeng Zhang,Wei Li,Yunhao Gao,Junjie Wang","doi":"10.1109/tnnls.2025.3589574","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3589574","url":null,"abstract":"Segment anything model (SAM), as a prompt-based image segmentation foundation model, demonstrates strong task versatility and domain generalization (DG) capabilities, providing a new direction for solving cross-scene segmentation tasks. However, SAM still has limitations in multispectral cross-domain segmentation tasks, mainly reflected in: 1) insufficient information utilization, which is reflected in the neglect of nonvisible spectral information and the shift information contained in source domain (SD) samples and target domain (TD) samples; and 2) lack of cross-domain strategies, which leads to insufficient cross-domain adaptation (DA) ability in downstream tasks. To address these challenges, we combine the respective advantages of masked autoencoder (MAE) and cross-domain strategies, propose an improved SAM DA network structure called domain information mining and state-guided adaptation network (DSAnet), aiming to enhance SAM's performance in multispectral cross-domain segmentation tasks from both data and task levels. At the data level, DSAnet incorporates a style masking learning component, which randomly masks image features and replaces them with domain-specific learnable tokens, integrated with the image reconstruction task, to mine the style information and domain invariance of the image itself. At the task level, DSAnet introduces domain state learning and style-guided segmentation: domain state learning, through a state sequence modeling approach, designs specific state representations for SD and TD to capture interdomain differences, thereby reducing task shift. Meanwhile, the learned domain state information can be directly applied to the inference stage. Style prompt segmentation guides the segmentation training process of SD images with TD style prompts, improving SAM's adaptability in cross-domain multispectral segmentation downstream tasks. Extensive experiments on three multitemporal multispectral image (MSI) datasets demonstrate the superiority of the proposed method compared to state-of-the-art cross-domain strategies and SAM variant methods.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"14 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144684268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Long Short-Term Financial Time Series Forecasting Based on Residual Multiscale TCN Sparse Expert Network and Informer.","authors":"Wuzhida Bao,Yuting Cao,Yin Yang,Shiping Wen","doi":"10.1109/tnnls.2025.3584369","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3584369","url":null,"abstract":"Due to the inherent high volatility and complexity of financial markets, traditional time series forecasting models face numerous challenges in handling both short- and long-term predictions in the stock market. Most traditional neural network-based financial prediction models are limited to short-term forecasting and struggle to capture long-term trends and global dependencies in the market fully. To address this, we propose a novel network architecture called ResMMoT-Informer. This model combines the strengths of the residual multiscale temporal convolutional network (TCN) sparse expert network (ResMMoT) and the Informer, enabling it to effectively capture multiscale local features and global dependencies in the stock market. ResMMoT achieves stable training through a residual structure and a sparse multiscale TCN expert network, allowing it to flexibly model complex temporal features and learn trends across different time-step scales. Meanwhile, the Informer optimizes long-sequence forecasting performance through an improved self-attention mechanism. Additionally, we introduce the wavelet noise reduction (WNR) method, further enhancing the model's robustness and prediction accuracy. In the experimental section, ablation experiments first validate the effectiveness and necessity of the proposed strategies and network structure. Subsequent comparison experiments on the NASDAQ100 dataset demonstrate that ResMMoT-Informer excels in both long- and short-term time series forecasting tasks in the stock market, with significantly better prediction accuracy and generalization ability than existing models. Compared to other popular neural network-based financial forecasting models, ResMMoT-Informer leads in prediction accuracy, time robustness, and interpretability, showcasing its cutting-edge advantage in contemporary research.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"32 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144684270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"D2Fed: Federated Semi-Supervised Learning With Dual-Role Additive Local Training and Dual-Perspective Global Aggregation.","authors":"Jingxin Mao,Yu Yang,Zhiwei Wei,Yanlong Bi,Rongqing Zhang","doi":"10.1109/tnnls.2025.3587942","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3587942","url":null,"abstract":"Federated semi-supervised learning (FSSL) has recently emerged as a promising approach for enhancing the performance of federated learning (FL) using ubiquitous unlabeled data. However, this approach encounters challenges when learning a global model using both fully labeled and fully unlabeled clients. Previous works overlook the dissimilarities between labeled and unlabeled clients, predominantly using shared parameters for local training across these two types of clients, thereby inducing intertask interference during local training. Moreover, these works typically adopt a single-perspective aggregation strategy, primarily focusing on data-volume-aware aggregation (i.e., FedAvg), leading to a lack of comprehensive consideration in model aggregation. In this article, we propose a novel FSSL method termed $text {D}^{{2}}text {Fed}$ , which addresses these issues by rethinking the roles of labeled clients and unlabeled ones to mitigate intertask interference during local training and by integrating client-type-aware with data-volume-aware to provide a more comprehensive perspective for model aggregation. Specifically, in local training, our proposed $text {D}^{{2}}text {Fed}$ distinguishes between the primary and accessory roles of labeled and unlabeled clients, respectively, performing dual-role additive local training (DALT) accordingly. In global aggregation, $text {D}^{{2}}text {Fed}$ uses a dual-perspective global aggregation (DGA) strategy, transitioning from data-volume-aware aggregation to client-type-aware aggregation. The proposed method simultaneously improves both local training and global model aggregation for FSSL without compromising privacy. We demonstrate the effectiveness and robustness of the proposed method through extensive experiments and elaborate ablation studies conducted on the CIFAR-10/100, SVHN, FMNIST, and STL-10 datasets. Experimental results show that $text {D}^{{2}}text {Fed}$ outperforms state-of-the-arts on five datasets under diverse data settings.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"143 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144684269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Video Prediction of Dynamic Physical Simulations With Pixel-Space Spatiotemporal Transformers.","authors":"Dean L Slack,G Thomas Hudson,Thomas Winterbottom,Noura Al Moubayed","doi":"10.1109/tnnls.2025.3585949","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3585949","url":null,"abstract":"Inspired by the performance and scalability of autoregressive large language models (LLMs), transformer-based models have seen recent success in the visual domain. This study investigates a transformer adaptation for video prediction with a simple end-to-end approach, comparing various spatiotemporal self-attention layouts. Focusing on causal modeling of physical simulations over time; a common shortcoming of existing video-generative approaches, we attempt to isolate spatiotemporal reasoning via physical object tracking metrics and unsupervised training on physical simulation datasets. We introduce a simple yet effective pure transformer model for autoregressive video prediction, utilizing continuous pixel-space representations for video prediction. Without the need for complex training strategies or latent feature-learning components, our approach significantly extends the time horizon for physically accurate predictions by up to 50% when compared with existing latent-space approaches, while maintaining comparable performance on common video quality metrics. In addition, we conduct interpretability experiments to identify network regions that encode information useful to perform accurate estimations of PDE simulation parameters via probing models, and find that this generalizes to the estimation of out-of-distribution simulation parameters. This work serves as a platform for further attention-based spatiotemporal modeling of videos via a simple, parameter efficient, and interpretable approach.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"18 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144684271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Copula Density Neural Estimation","authors":"Nunzio A. Letizia, Nicola Novello, Andrea M. Tonello","doi":"10.1109/tnnls.2025.3585755","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3585755","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"28 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144684465","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Adaptive Neighborhood-Resonated Graph Convolution Network for Undirected Weighted Graph Representation.","authors":"Jiufang Chen,Ye Yuan,Xin Luo,Xinbo Gao","doi":"10.1109/tnnls.2025.3589224","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3589224","url":null,"abstract":"An undirected weighted graph (UWG) is the fundamental data representation in various real applications. A graph convolution network is frequently utilized for representation learning to a UWG. Nevertheless, existing graph convolutional networks (GCNs) only consider a node's neighborhood during the embedding propagation, which regrettably decreases its representation learning capability due to the information loss in the modeling phase. Motivated by this discovery, this study proposes an adaptive neighborhood-resonated graph convolution network (ANR-GCN) with the following ideas: 1) establishing the weighted embedding propagation with the consideration of link weights in a UWG, thereby incorporating the interaction strength of each node pair into the ANR-GCN model; 2) building the neighborhood-regularization (NR) to make each node resonate with its neighborhoods, thus reinforcing the informative neighborhood information for improving the ANR-GCN's representation capability to the complex topology of the target UWG; and 3)diversifying the NR effects following the attention principle for guaranteeing the ANR-GCN's learning capacity. The proposed ANR-GCN's representation learning ability to a UWG is theoretically guaranteed from the perspectives of bounded generalization error and uniform stability. Extensive experiments on four UWG datasets illustrate that the proposed ANR-GCN significantly outperforms state-of-the-art GCNs in missing edge detection in a UWG, which evidently demonstrates its superior performance.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"103 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144684247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"PolicyMamba: Localized Policy Attention With State Space Model for Land Cover Classification.","authors":"Muhammad Ahmad,Manuel Mazzara,Salvatore Distefano,Adil Mehmood Khan,Muhammad Hassaan Farooq Butt,Danfeng Hong","doi":"10.1109/tnnls.2025.3586836","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3586836","url":null,"abstract":"Multihead self-attention and cross-attention mechanisms often suffer from computational inefficiencies, limited scalability, and suboptimal contextual understanding, particularly in hyperspectral image (HSI) classification. These mechanisms struggle to effectively capture long-range dependencies while maintaining computational feasibility due to the quadratic complexity of self-attention. To address these challenges, this work proposes PolicyMamba, a spectral-spatial mamba model enhanced with a localized policy attention mechanism. This mechanism reduces computational overhead by restricting attention to nonoverlapping localized regions and enforcing sparsity constraints, ensuring that only the most informative interactions are retained. A hierarchical aggregation strategy further integrates patch-wise attention outputs, preserving spectral-spatial correlations across scales. In addition, a sliding window patch process enhances local feature continuity while mitigating information loss. The PolicyMamba framework integrates spectral-spatial token generation, token enhancement, localized attention, and state transition modules, significantly improving HSI feature representation. Extensive experiments demonstrate that PolicyMamba achieves superior classification accuracy, outperforming conventional and state-of-the-art methods in land cover classification (LCC) by efficiently modeling intricate dependencies in HSI data.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"1 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144684248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ChebMixer: Efficient Graph Representation Learning With MLP Mixer","authors":"Xiaoyan Kui, Haonan Yan, Qinsong Li, Min Zhang, Liming Chen, Beiji Zou","doi":"10.1109/tnnls.2025.3589316","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3589316","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"17 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144684932","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ODMTCNet: An Interpretable Multiview Deep Neural Network Architecture for Feature Representation","authors":"Lei Gao, Zheng Guo, Ling Guan","doi":"10.1109/tnnls.2025.3588327","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3588327","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"23 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144677421","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"NACHOS: Neural Architecture Search for Hardware-Constrained Early-Exit Neural Networks","authors":"Matteo Gambella, Jary Pomponi, Simone Scardapane, Manuel Roveri","doi":"10.1109/tnnls.2025.3588558","DOIUrl":"https://doi.org/10.1109/tnnls.2025.3588558","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"102 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2025-07-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144677423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}