Pub Date : 2026-04-23DOI: 10.1109/tnnls.2026.3682991
Chenqiu Zhao,Guanfang Dong,Anup Basu
Learning intractable distributions in high-dimensional spaces remains a fundamental challenge. While prevalent deep learning methods often rely on restrictive prior assumptions, we propose a novel differentiable method that approximates intractable distributions using a Gaussian mixture model (GMM) by minimizing Kullback-Leibler (KL) divergence. In particular, a novel Monte Carlo marginalization (MCMarg) method is proposed to address the computational complexity of the KL divergence, which is unacceptable in a high-dimensional space. In addition, kernel density estimation (KDE) is utilized to ensure the differentiability of the optimization process because the target distribution is intractable. The proposed approach is a powerful and differentiable tool for learning complex distributions, which shifts the paradigm from network-dependent approximation to direct, network-free distribution learning. Comprehensive experiments demonstrate the superior properties of the proposed approach. By replacing standard priors in pretrained VAEs, our method achieves a significant improvement of approximately 10 points in FID scores. Remarkably, the model enables image generation without using a neural network, achieving an FID of 22 on the MNIST dataset. On the CIFAR-10 benchmark, our method achieves an FID score of 2.69, outperforming several state-of-the-art deep generative models. To the best of our knowledge, the proposed MCMarg is the first attempt at image generation without using a deep learning network.
{"title":"Monte Carlo Marginalization: A Differentiable Method to Learn High-Dimensional Distributions.","authors":"Chenqiu Zhao,Guanfang Dong,Anup Basu","doi":"10.1109/tnnls.2026.3682991","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3682991","url":null,"abstract":"Learning intractable distributions in high-dimensional spaces remains a fundamental challenge. While prevalent deep learning methods often rely on restrictive prior assumptions, we propose a novel differentiable method that approximates intractable distributions using a Gaussian mixture model (GMM) by minimizing Kullback-Leibler (KL) divergence. In particular, a novel Monte Carlo marginalization (MCMarg) method is proposed to address the computational complexity of the KL divergence, which is unacceptable in a high-dimensional space. In addition, kernel density estimation (KDE) is utilized to ensure the differentiability of the optimization process because the target distribution is intractable. The proposed approach is a powerful and differentiable tool for learning complex distributions, which shifts the paradigm from network-dependent approximation to direct, network-free distribution learning. Comprehensive experiments demonstrate the superior properties of the proposed approach. By replacing standard priors in pretrained VAEs, our method achieves a significant improvement of approximately 10 points in FID scores. Remarkably, the model enables image generation without using a neural network, achieving an FID of 22 on the MNIST dataset. On the CIFAR-10 benchmark, our method achieves an FID score of 2.69, outperforming several state-of-the-art deep generative models. To the best of our knowledge, the proposed MCMarg is the first attempt at image generation without using a deep learning network.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"25 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147735246","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}
Pub Date : 2026-04-23DOI: 10.1109/tnnls.2026.3683363
Jia Zhang,Bo Peng,Xi Wu,Chenchen He
Recent advancements in weakly supervised semantic segmentation (WSSS) have shown promise by using the contrastive language-image pretraining (CLIP) model to generate pseudo-labels. However, directly applying the CLIP model without considering interclass relationships in downstream tasks has resulted in suboptimal transferability and generalization. To address these challenges, we propose CLIP graph adapter (CLIP-GA), a novel approach that integrates both textual and visual structural knowledge to generate high-quality initial class activation maps (CAMs) for each object class. Our method introduces a dual-graph adaptive strategy, comprising a textual subgraph and a visual subgraph and employs cross-modal graph attention (CGA) for effective fusion. The framework includes three specialized loss functions that help to capture more complete object regions while minimizing the activation of background areas closely related to foreground objects. In addition, we implement the superpixel consistency to refine pseudo-labels and introduce a graph reasoning attention (GRA) module to build global contextual relationships within visual features for the segmentation network. Extensive experiments on the PASCAL VOC 2012 and MS COCO 2014 datasets have convincingly demonstrated the effectiveness of CLIP-GA compared with other state-of-the-art methods. Our code is provided at: https://github.com/JIA-ZHANG666/CLIP-GA.
{"title":"CLIP Graph Adaptor: A Dual-Graph Adapted Visual-Language Model for Weakly Supervised Semantic Segmentation.","authors":"Jia Zhang,Bo Peng,Xi Wu,Chenchen He","doi":"10.1109/tnnls.2026.3683363","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3683363","url":null,"abstract":"Recent advancements in weakly supervised semantic segmentation (WSSS) have shown promise by using the contrastive language-image pretraining (CLIP) model to generate pseudo-labels. However, directly applying the CLIP model without considering interclass relationships in downstream tasks has resulted in suboptimal transferability and generalization. To address these challenges, we propose CLIP graph adapter (CLIP-GA), a novel approach that integrates both textual and visual structural knowledge to generate high-quality initial class activation maps (CAMs) for each object class. Our method introduces a dual-graph adaptive strategy, comprising a textual subgraph and a visual subgraph and employs cross-modal graph attention (CGA) for effective fusion. The framework includes three specialized loss functions that help to capture more complete object regions while minimizing the activation of background areas closely related to foreground objects. In addition, we implement the superpixel consistency to refine pseudo-labels and introduce a graph reasoning attention (GRA) module to build global contextual relationships within visual features for the segmentation network. Extensive experiments on the PASCAL VOC 2012 and MS COCO 2014 datasets have convincingly demonstrated the effectiveness of CLIP-GA compared with other state-of-the-art methods. Our code is provided at: https://github.com/JIA-ZHANG666/CLIP-GA.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"27 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147735248","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}
Pub Date : 2026-04-22DOI: 10.1109/tnnls.2026.3684321
Ziqiao Weng,Weidong Cai,Bo Zhou
Federated learning (FL) enables privacy-preserving collaborative model training without direct data sharing. Model-heterogeneous FL (MHFL) enables clients to train personalized models with heterogeneous architectures, but existing methods mainly rely on centralized aggregation or require partially identical architectures, limiting scalability and efficiency. Current peer-to-peer (P2P) FL frameworks, though removing server dependence, have not been adapted to heterogeneous models and suffer from model drift and knowledge dilution. To address these challenges, we propose FedSKD, a novel P2P MHFL framework for medical image classification that facilitates direct knowledge exchange through round-robin model circulation, eliminating the need for centralized aggregation while allowing fully heterogeneous model architectures across clients. FedSKD's key innovation lies in multidimensional similarity knowledge distillation (SKD), which enables bidirectional cross-client knowledge transfer at batch, pixel/voxel, and region levels for heterogeneous models in FL. This approach mitigates catastrophic forgetting and model drift through progressive reinforcement and distribution alignment while preserving model heterogeneity. Extensive evaluations on fMRI-based autism spectrum disorder (ASD) diagnosis and skin lesion classification demonstrate that FedSKD outperforms state-of-the-art heterogeneous and homogeneous FL baselines, achieving superior personalization and cross-institutional generalization. These findings underscore FedSKD's potential as a scalable and robust solution for real-world medical FL.
{"title":"FedSKD: Aggregation-Free Model-Heterogeneous Federated Learning via Multidimensional Similarity Knowledge Distillation for Medical Image Classification.","authors":"Ziqiao Weng,Weidong Cai,Bo Zhou","doi":"10.1109/tnnls.2026.3684321","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3684321","url":null,"abstract":"Federated learning (FL) enables privacy-preserving collaborative model training without direct data sharing. Model-heterogeneous FL (MHFL) enables clients to train personalized models with heterogeneous architectures, but existing methods mainly rely on centralized aggregation or require partially identical architectures, limiting scalability and efficiency. Current peer-to-peer (P2P) FL frameworks, though removing server dependence, have not been adapted to heterogeneous models and suffer from model drift and knowledge dilution. To address these challenges, we propose FedSKD, a novel P2P MHFL framework for medical image classification that facilitates direct knowledge exchange through round-robin model circulation, eliminating the need for centralized aggregation while allowing fully heterogeneous model architectures across clients. FedSKD's key innovation lies in multidimensional similarity knowledge distillation (SKD), which enables bidirectional cross-client knowledge transfer at batch, pixel/voxel, and region levels for heterogeneous models in FL. This approach mitigates catastrophic forgetting and model drift through progressive reinforcement and distribution alignment while preserving model heterogeneity. Extensive evaluations on fMRI-based autism spectrum disorder (ASD) diagnosis and skin lesion classification demonstrate that FedSKD outperforms state-of-the-art heterogeneous and homogeneous FL baselines, achieving superior personalization and cross-institutional generalization. These findings underscore FedSKD's potential as a scalable and robust solution for real-world medical FL.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"23 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147733980","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}
Pub Date : 2026-04-22DOI: 10.1109/tnnls.2026.3684886
Binbin Huang,Teng Bao,Feiyi Chen,Lingbin Wang,Xunqing Huang,Yuyu Yin,Xiaoying Shi,Shangguang Wang,Shuiguang Deng
The growth of large models demands multinode cooperation during training and inference processes. The computing node failures can interrupt these processes, subsequently causing information loss and prolonging the execution time. To reduce the prohibitively large overhead incurred by the computing nodes failures, the accurate prediction of computing node failure is vital, which can help to avert potential large overhead, service interruptions, and negative customer experiences. Existing solutions of computing nodes failure prediction mainly focus on utilizing state-of-the-art time-series models to enhance the performance of computing node failure prediction. However, on the one hand, they could not capture the causal relationship between device over-utilization and node failures; On the other hand, they fail to extract the complex spatial-temporal cascading correlations among computing node failure events. These limits can degrade the performance of computing node failure prediction. To address these above problems, this article makes an effort to focus on designing a continuous-time dynamic graphs-based computing node failures prediction (CTDG-NFP) scheme, to accurately predict in dynamic cluster environments. Specifically, the CTDG-NFP scheme first designs a novel multiple-dimensional feature-biased neighbor sampling method, which jointly considers CPU utilization-biased, memory utilization-biased, temporal-biased and spatial-biased, to sample relevant context. Then, the CTDG-NFP scheme extracts diverse computing node failure motifs by multiple-dimensional feature-biased-based long-short-path walk method and set-based anonymization method. Finally, the CTDG-NFP scheme adopts time encoder to encode these motifs, and thereby extracting the complex spatial-temporal correlations among computing node failure events. On this basis, contrastive learning is adopted to train the computing node failure prediction model. Extensive evaluations with various real-world failure traces demonstrate the CTDG-NFP scheme can achieve superior performance in terms of six widely used performance metrics compared with the SOTA node failure prediction methods.
{"title":"Computing Node Failure Prediction Based on Continuous-Time Dynamic Graph.","authors":"Binbin Huang,Teng Bao,Feiyi Chen,Lingbin Wang,Xunqing Huang,Yuyu Yin,Xiaoying Shi,Shangguang Wang,Shuiguang Deng","doi":"10.1109/tnnls.2026.3684886","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3684886","url":null,"abstract":"The growth of large models demands multinode cooperation during training and inference processes. The computing node failures can interrupt these processes, subsequently causing information loss and prolonging the execution time. To reduce the prohibitively large overhead incurred by the computing nodes failures, the accurate prediction of computing node failure is vital, which can help to avert potential large overhead, service interruptions, and negative customer experiences. Existing solutions of computing nodes failure prediction mainly focus on utilizing state-of-the-art time-series models to enhance the performance of computing node failure prediction. However, on the one hand, they could not capture the causal relationship between device over-utilization and node failures; On the other hand, they fail to extract the complex spatial-temporal cascading correlations among computing node failure events. These limits can degrade the performance of computing node failure prediction. To address these above problems, this article makes an effort to focus on designing a continuous-time dynamic graphs-based computing node failures prediction (CTDG-NFP) scheme, to accurately predict in dynamic cluster environments. Specifically, the CTDG-NFP scheme first designs a novel multiple-dimensional feature-biased neighbor sampling method, which jointly considers CPU utilization-biased, memory utilization-biased, temporal-biased and spatial-biased, to sample relevant context. Then, the CTDG-NFP scheme extracts diverse computing node failure motifs by multiple-dimensional feature-biased-based long-short-path walk method and set-based anonymization method. Finally, the CTDG-NFP scheme adopts time encoder to encode these motifs, and thereby extracting the complex spatial-temporal correlations among computing node failure events. On this basis, contrastive learning is adopted to train the computing node failure prediction model. Extensive evaluations with various real-world failure traces demonstrate the CTDG-NFP scheme can achieve superior performance in terms of six widely used performance metrics compared with the SOTA node failure prediction methods.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"246 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147733983","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}
Pub Date : 2026-04-22DOI: 10.1109/tnnls.2026.3683398
Ruinan Jin, Minghui Chen, Qiong Zhang, Xiaoxiao Li
{"title":"Forgettable Federated Linear Learning With Certified Data Unlearning","authors":"Ruinan Jin, Minghui Chen, Qiong Zhang, Xiaoxiao Li","doi":"10.1109/tnnls.2026.3683398","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3683398","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"22 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147735977","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}
Pub Date : 2026-04-22DOI: 10.1109/tnnls.2026.3680732
Zhili Zhao,Li Wan,Xupeng Liu,Ruiyi Yan,Shaomeng Wang
In node classification, traditional graph neural networks (GNNs) typically assume implicit homophily, indicating that intraclass nodes are likely connected. However, real-world graphs frequently exhibit heterophily, in which interclass nodes are also commonly connected. To address this challenge, recent methods have adopted approaches such as expanding local neighborhoods and employing adaptive message aggregation to enhance the GNN performance on heterophily graphs. Nevertheless, these methods are restricted by the homophily assumption and fail to effectively capture long-range dependencies (e.g., widely separated intraclass nodes) and insufficiently leverage the graph topology. This study investigates the performance differences of GNN when it is applied to both homophily and heterophily graphs and finds that the distinguishability of neighborhood label distributions (NLDs) exhibits a significant correlation with the accuracy of node classification. To assess the impact of NLD on node classification, this study proposes a novel homophily metric based on node distinguishability. Subsequently, this study introduces a new GNN model named NLD-based GNN (NLDGNN) for node classification. First, NLDGNN initializes node representations by integrating node features with node NLDs. To address long-range dependencies in heterophily graphs, NLDGNN utilizes the global label relationship matrix with low-rank characteristics for global message passing. By combining the attention scores derived from the initial node representations, NLDGNN constructs the global label relationship matrix for enhanced message passing, thereby improving the expressiveness of node representations. Experimental results indicate that NLDGNN outperforms existing GNN models on both real-world homophily and heterophily graphs. The code of this study is available at https://github.com/wanli6/NLDGNN.
{"title":"Node Classification in GNNs: Impact of Neighborhood Label Distribution on Homophily and Heterophily.","authors":"Zhili Zhao,Li Wan,Xupeng Liu,Ruiyi Yan,Shaomeng Wang","doi":"10.1109/tnnls.2026.3680732","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3680732","url":null,"abstract":"In node classification, traditional graph neural networks (GNNs) typically assume implicit homophily, indicating that intraclass nodes are likely connected. However, real-world graphs frequently exhibit heterophily, in which interclass nodes are also commonly connected. To address this challenge, recent methods have adopted approaches such as expanding local neighborhoods and employing adaptive message aggregation to enhance the GNN performance on heterophily graphs. Nevertheless, these methods are restricted by the homophily assumption and fail to effectively capture long-range dependencies (e.g., widely separated intraclass nodes) and insufficiently leverage the graph topology. This study investigates the performance differences of GNN when it is applied to both homophily and heterophily graphs and finds that the distinguishability of neighborhood label distributions (NLDs) exhibits a significant correlation with the accuracy of node classification. To assess the impact of NLD on node classification, this study proposes a novel homophily metric based on node distinguishability. Subsequently, this study introduces a new GNN model named NLD-based GNN (NLDGNN) for node classification. First, NLDGNN initializes node representations by integrating node features with node NLDs. To address long-range dependencies in heterophily graphs, NLDGNN utilizes the global label relationship matrix with low-rank characteristics for global message passing. By combining the attention scores derived from the initial node representations, NLDGNN constructs the global label relationship matrix for enhanced message passing, thereby improving the expressiveness of node representations. Experimental results indicate that NLDGNN outperforms existing GNN models on both real-world homophily and heterophily graphs. The code of this study is available at https://github.com/wanli6/NLDGNN.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"25 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147733981","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}
Formal verification using temporal logics such as computation tree logic (CTL) is essential for validating safety and correctness in complex systems. However, traditional model-checking techniques face severe scalability limitations due to the state explosion problem and their reliance on exhaustive symbolic traversal. Moreover, existing learning-based verification methods often lack formal guarantees and interpretability. These challenges create a pressing need for scalable, learning-based verification methods that preserve verification reliability while improving computational efficiency. This article introduces a novel deep reinforcement learning (DRL)-based model checking framework that learns to verify CTL formulas directly through interaction with system models. Unlike traditional symbolic model checkers such as NuSMV, the proposed DRL-CTL checker trained using proximal policy optimization (PPO) interprets CTL semantics over system models represented as Kripke structures without performing symbolic state-space traversal at inference time. Reward functions are designed for individual CTL operators, and fixed-point reasoning is incorporated to handle global temporal properties such as $AG(phi)$ and $EG(phi)$ . Experimental results show that the proposed method achieves near-constant inference time of approximately 2 ms per formula on an Intel Core i9-13900K CPU (24 cores, 3.0 GHz), 64 GB RAM, NVIDIA RTX 4090 GPU (24 GB VRAM), reduces verification time by up to 90% compared with traditional model checkers, and scales to models with more than $10^{1192}$ reachable states. The framework also produces witnesses and counterexamples and yields verification outcomes identical to those of symbolic checkers in our experiments. These results highlight the potential of DRL to serve as a scalable, efficient, and explainable alternative to classical CTL model checking.
{"title":"Scalable and Efficient Deep Reinforcement Learning-Based Model Checker for Computation Tree Logic.","authors":"Ghalya Alwhishi,Jamal Bentahar,Amine Andam,Ahmed Elwhishi,Mustapha Hedabou","doi":"10.1109/tnnls.2026.3683573","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3683573","url":null,"abstract":"Formal verification using temporal logics such as computation tree logic (CTL) is essential for validating safety and correctness in complex systems. However, traditional model-checking techniques face severe scalability limitations due to the state explosion problem and their reliance on exhaustive symbolic traversal. Moreover, existing learning-based verification methods often lack formal guarantees and interpretability. These challenges create a pressing need for scalable, learning-based verification methods that preserve verification reliability while improving computational efficiency. This article introduces a novel deep reinforcement learning (DRL)-based model checking framework that learns to verify CTL formulas directly through interaction with system models. Unlike traditional symbolic model checkers such as NuSMV, the proposed DRL-CTL checker trained using proximal policy optimization (PPO) interprets CTL semantics over system models represented as Kripke structures without performing symbolic state-space traversal at inference time. Reward functions are designed for individual CTL operators, and fixed-point reasoning is incorporated to handle global temporal properties such as $AG(phi)$ and $EG(phi)$ . Experimental results show that the proposed method achieves near-constant inference time of approximately 2 ms per formula on an Intel Core i9-13900K CPU (24 cores, 3.0 GHz), 64 GB RAM, NVIDIA RTX 4090 GPU (24 GB VRAM), reduces verification time by up to 90% compared with traditional model checkers, and scales to models with more than $10^{1192}$ reachable states. The framework also produces witnesses and counterexamples and yields verification outcomes identical to those of symbolic checkers in our experiments. These results highlight the potential of DRL to serve as a scalable, efficient, and explainable alternative to classical CTL model checking.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"13 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147731258","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}
Pub Date : 2026-04-21DOI: 10.1109/tnnls.2026.3675892
Leilei Cui, Zhong-Ping Jiang, Petter N. Kolm, Grégoire G. Macqueron
{"title":"A Fully Data-Driven Value Iteration for Stochastic LQR: Convergence, Robustness, and Stability","authors":"Leilei Cui, Zhong-Ping Jiang, Petter N. Kolm, Grégoire G. Macqueron","doi":"10.1109/tnnls.2026.3675892","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3675892","url":null,"abstract":"","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"21 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147731795","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}
Pub Date : 2026-04-21DOI: 10.1109/tnnls.2026.3684128
Jianqi Zhong,Junyu Shi,Wenming Cao
Graph Convolutional Networks (GCNs) have exhibited considerable promise in 3-D skeleton-based human motion prediction. Based on the intuitive observation that human motion can be delineated through the physical interconnections among human joints, many previous works have designed multiscale graphs to learn the relationships and constraints between different graph scales, obtaining encouraging results for human motion prediction. However, these fixed multiscale graphs obtain new scale graphs by merging adjacent human joint information, ignoring implicit semantic information during dynamic movements. Furthermore, human joint correlations tend to vary randomly as the depth of the multiscale clustering graph increases, which contradicts the design concept of fixed multiscale graphs. To address these limitations, we explore a novel correlation-based multiscale graph clustering network (CMGC) for adaptive multiscale graph representation learning. Given a human joints graph, the goal of CMGC is first to generate more new graphs representing motion correlations adaptively at different scale levels and then selectively restore the derived graph scales to the original human joints graphs, which enables various motion features extraction. Moreover, we introduce the discrete wavelet transform (DWT) to compensate for the signal loss caused by discrete cosine transform (DCT) domain modeling from human motion. The CMGC gives rise to gratifying performances with the adaptive multiscale graph. Extensive experiments reveal that CMGC outperforms state-of-the-art methods by 11.2%, 10.1%, and 11.2% of 3-D mean per joint position error (MPJPE) on average on Human 3.6M, CMU Mocap, and 3DPW datasets, respectively. We also test the mean angle error (MAE) on Human3.6M, which is lower by 6.5% than previous methods. Our code is released at https://github.com/JunyuShi02/CMGC.
{"title":"Multiscale Graph Redefining: Correlation-Based Multiscale Graph Clustering Network for Human Motion Prediction.","authors":"Jianqi Zhong,Junyu Shi,Wenming Cao","doi":"10.1109/tnnls.2026.3684128","DOIUrl":"https://doi.org/10.1109/tnnls.2026.3684128","url":null,"abstract":"Graph Convolutional Networks (GCNs) have exhibited considerable promise in 3-D skeleton-based human motion prediction. Based on the intuitive observation that human motion can be delineated through the physical interconnections among human joints, many previous works have designed multiscale graphs to learn the relationships and constraints between different graph scales, obtaining encouraging results for human motion prediction. However, these fixed multiscale graphs obtain new scale graphs by merging adjacent human joint information, ignoring implicit semantic information during dynamic movements. Furthermore, human joint correlations tend to vary randomly as the depth of the multiscale clustering graph increases, which contradicts the design concept of fixed multiscale graphs. To address these limitations, we explore a novel correlation-based multiscale graph clustering network (CMGC) for adaptive multiscale graph representation learning. Given a human joints graph, the goal of CMGC is first to generate more new graphs representing motion correlations adaptively at different scale levels and then selectively restore the derived graph scales to the original human joints graphs, which enables various motion features extraction. Moreover, we introduce the discrete wavelet transform (DWT) to compensate for the signal loss caused by discrete cosine transform (DCT) domain modeling from human motion. The CMGC gives rise to gratifying performances with the adaptive multiscale graph. Extensive experiments reveal that CMGC outperforms state-of-the-art methods by 11.2%, 10.1%, and 11.2% of 3-D mean per joint position error (MPJPE) on average on Human 3.6M, CMU Mocap, and 3DPW datasets, respectively. We also test the mean angle error (MAE) on Human3.6M, which is lower by 6.5% than previous methods. Our code is released at https://github.com/JunyuShi02/CMGC.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"322 1","pages":""},"PeriodicalIF":10.4,"publicationDate":"2026-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147731259","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：