Neural Networks最新文献_第7页

Riemannian manifold-based disentangled representation learning for multi-site functional connectivity analysis.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-29 DOI: 10.1016/j.neunet.2024.106945

Wenyang Li, Mingliang Wang, Mingxia Liu, Qingshan Liu

{"title":"Riemannian manifold-based disentangled representation learning for multi-site functional connectivity analysis.","authors":"Wenyang Li, Mingliang Wang, Mingxia Liu, Qingshan Liu","doi":"10.1016/j.neunet.2024.106945","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.106945","url":null,"abstract":"Functional connectivity (FC), derived from resting-state functional magnetic resonance imaging (rs-fMRI), has been widely used to characterize brain abnormalities in disorders. FC is usually defined as a correlation matrix that is a symmetric positive definite (SPD) matrix lying on the Riemannian manifold. Recently, a number of learning-based methods have been proposed for FC analysis, while the geometric properties of Riemannian manifold have not yet been fully explored in previous studies. Also, most existing methods are designed to target one imaging site of fMRI data, which may result in limited training data for learning reliable and robust models. In this paper, we propose a novel Riemannian Manifold-based Disentangled Representation Learning (RM-DRL) framework which is capable of learning invariant representations from fMRI data across multiple sites for brain disorder diagnosis. In RM-DRL, we first employ an SPD-based encoder module to learn a latent unified representation of FC from different sites, which can preserve the Riemannian geometry of the SPD matrices. In latent space, a disentangled representation module is then designed to split the learned features into domain-specific and domain-invariant parts, respectively. Finally, a decoder module is introduced to ensure that sufficient information can be preserved during disentanglement learning. These designs allow us to introduce four types of training objectives to improve the disentanglement learning. Our RM-DRL method is evaluated on the public multi-site ABIDE dataset, showing superior performance compared with several state-of-the-art methods.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"183 ","pages":"106945"},"PeriodicalIF":6.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142792335","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}

引用次数: 0

Illumination-Guided progressive unsupervised domain adaptation for low-light instance segmentation.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-29 DOI: 10.1016/j.neunet.2024.106958

Yi Zhang, Jichang Guo, Huihui Yue, Sida Zheng, Chonghao Liu

{"title":"Illumination-Guided progressive unsupervised domain adaptation for low-light instance segmentation.","authors":"Yi Zhang, Jichang Guo, Huihui Yue, Sida Zheng, Chonghao Liu","doi":"10.1016/j.neunet.2024.106958","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.106958","url":null,"abstract":"Due to limited photons, low-light environments pose significant challenges for computer vision tasks. Unsupervised domain adaptation offers a potential solution, but struggles with domain misalignment caused by inadequate utilization of features at different stages. To address this, we propose an Illumination-Guided Progressive Unsupervised Domain Adaptation method, called IPULIS, for low-light instance segmentation by progressively exploring the alignment of features at image-, instance-, and pixel-levels between normal- and low-light conditions under illumination guidance. This is achieved through: (1) an Illumination-Guided Domain Discriminator (IGD) for image-level feature alignment using retinex-derived illumination maps, (2) a Foreground Focus Module (FFM) incorporating global information with local center features to facilitate instance-level feature alignment, and (3) a Contour-aware Domain Discriminator (CAD) for pixel-level feature alignment by matching contour vertex features from a contour-based model. By progressively deploying these modules, IPULIS achieves precise feature alignment, leading to high-quality instance segmentation. Experimental results demonstrate that our IPULIS achieves state-of-the-art performance on real-world low-light dataset LIS.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"183 ","pages":"106958"},"PeriodicalIF":6.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142787485","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}

引用次数: 0

Hybrid contrastive multi-scenario learning for multi-task sequential-dependence recommendation.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-29 DOI: 10.1016/j.neunet.2024.106953

Qingqing Yi, Lunwen Wu, Jingjing Tang, Yujian Zeng, Zengchun Song

{"title":"Hybrid contrastive multi-scenario learning for multi-task sequential-dependence recommendation.","authors":"Qingqing Yi, Lunwen Wu, Jingjing Tang, Yujian Zeng, Zengchun Song","doi":"10.1016/j.neunet.2024.106953","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.106953","url":null,"abstract":"Multi-scenario and multi-task learning are crucial in industrial recommendation systems to deliver high-quality recommendations across diverse scenarios with minimal computational overhead. However, conventional models often fail to effectively leverage cross-scenario information, limiting their representational capabilities. Additionally, multi-step conversion tasks in real-world applications face challenges from sequential dependencies and increased data sparsity, particularly in later stages. To address these issues, we propose a Hybrid Contrastive Multi-scenario learning framework for Multi-task Sequential-dependence Recommendation (HCM2SR). In the scenario layer, hybrid contrastive learning captures both shared and scenario-specific information, while a scenario-aware multi-gate network enhances representations by evaluating cross-scenario relevance. In the task layer, an adaptive multi-task network transfers knowledge across sequential stages, mitigating data sparsity in long-path conversions. Extensive experiments on two public datasets and one industrial dataset validate the effectiveness of HCM2SR, with ablation studies confirming the contribution of each component.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"183 ","pages":"106953"},"PeriodicalIF":6.0,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142796515","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}

引用次数: 0

Estimating global phase synchronization by quantifying multivariate mutual information and detecting network structure.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-28 DOI: 10.1016/j.neunet.2024.106984

Zhaohui Li, Yanyu Xing, Xinyan Wang, Yunlu Cai, Xiaoxia Zhou, Xi Zhang

{"title":"Estimating global phase synchronization by quantifying multivariate mutual information and detecting network structure.","authors":"Zhaohui Li, Yanyu Xing, Xinyan Wang, Yunlu Cai, Xiaoxia Zhou, Xi Zhang","doi":"10.1016/j.neunet.2024.106984","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.106984","url":null,"abstract":"In neuroscience, phase synchronization (PS) is a crucial mechanism that facilitates information processing and transmission between different brain regions. Specifically, global phase synchronization (GPS) characterizes the degree of PS among multivariate neural signals. In recent years, several GPS methods have been proposed. However, they primarily focus on the collective synchronization behavior of multivariate neural signals, while neglecting the structural difference between oscillator networks. Therefore, in this paper, we introduce a method named total correlation-based synchronization (TCS) to quantify GPS intensity by examining network organization. To evaluate the performance of TCS, we conducted simulations using the Rössler model and compared it to three existing methods: circular omega complexity, hyper-torus synchrony, and symbolic phase difference and permutation entropy. The results indicate that TCS outperforms the other methods at distinguishing the GPS intensity between networks with similar structures. And it offers insight into the separation and integration behavior of signals during synchronization. Furthermore, to validate this method with experimental data, TCS was applied to analyze the GPS variation of multichannel stereo-electroencephalography (SEEG) signals recorded from onset zones of patients with temporal lobe epilepsy. It was observed that the termination of seizures was associated with the increased GPS and the integration of brain regions. Taken together, TCS offers an alternative way to measure GPS of multivariate signals, which may shed new lights on the mechanism of brain functions and neurological disorders, such as learning, memory, epilepsy, and Alzheimer's disease.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"183 ","pages":"106984"},"PeriodicalIF":6.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142773941","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}

引用次数: 0

Multi-hop interpretable meta learning for few-shot temporal knowledge graph completion.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-28 DOI: 10.1016/j.neunet.2024.106981

Luyi Bai, Shuo Han, Lin Zhu

{"title":"Multi-hop interpretable meta learning for few-shot temporal knowledge graph completion.","authors":"Luyi Bai, Shuo Han, Lin Zhu","doi":"10.1016/j.neunet.2024.106981","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.106981","url":null,"abstract":"Multi-hop path completion is a key part of temporal knowledge graph completion, which aims to infer complex relationships and obtain interpretable completion results. However, the traditional multi-hop path completion models mainly focus on the static knowledge graph with sufficient relationship instances, and does not consider the impact of timestamp information on the completion path, and is not suitable for few-shot relations. These limitations make the performance of these models not good when dealing with few-shot relationships in temporal knowledge graphs. In order to issue these challenges, we propose the Few-shot Temporal knowledge graph completion model based on the Multi-hop Interpretable meta-learning(FTMI). First, by aggregating the multi-hop neighbor information of the task relationship to generate a time-aware entity representation to enhance the task entity representation, the introduction of the timestamp information dimension enables the FTMI model to understand and deal with the impact of time changes on entities and relationships. In addition, time-aware entity pair representations are encoded using Transformer. At the same time, the specific representation of task relationship is generated by means of mean pooling layer aggregation. In addition, the model applies the reinforcement learning framework to the whole process of multi-hop path completion, constructs the strategy network, designs the new reward function to achieve the balance between path novelty and length, and helps Agent find the optimal path, thus realizing the completion of the temporal knowledge graph with few samples. In the training process, meta-learning is used to enable the model to quickly adapt to new tasks in the case of few samples. A huge number of experiments were carried out on two datasets to validate the model's validity.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"183 ","pages":"106981"},"PeriodicalIF":6.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142773971","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}

引用次数: 0

Event-based adaptive fixed-time optimal control for saturated fault-tolerant nonlinear multiagent systems via reinforcement learning algorithm.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-28 DOI: 10.1016/j.neunet.2024.106952

Huarong Yue, Jianwei Xia, Jing Zhang, Ju H Park, Xiangpeng Xie

{"title":"Event-based adaptive fixed-time optimal control for saturated fault-tolerant nonlinear multiagent systems via reinforcement learning algorithm.","authors":"Huarong Yue, Jianwei Xia, Jing Zhang, Ju H Park, Xiangpeng Xie","doi":"10.1016/j.neunet.2024.106952","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.106952","url":null,"abstract":"This article investigates the problem of adaptive fixed-time optimal consensus tracking control for nonlinear multiagent systems (MASs) affected by actuator faults and input saturation. To achieve optimal control, reinforcement learning (RL) algorithm which is implemented based on neural network (NN) is employed. Under the actor-critic structure, an innovative simple positive definite function is constructed to obtain the upper bound of the estimation error of the actor-critic NN updating law, which is crucial for analyzing fixed-time stabilization. Furthermore, auxiliary functions and estimation laws are designed to eliminate the coupling effects resulting from actuator faults and input saturation. Meanwhile, a novel event-triggered mechanism (ETM) that incorporates the consensus tracking errors into the threshold is proposed, thereby effectively conserving communication resources. Based on this, a fixed-time event-triggered control scheme grounded in RL is proposed through the integration of the backstepping technique and fixed-time theory. It is demonstrated that the consensus tracking errors converge to a specified range in a fixed time and all signals within the closed-loop systems are bounded. Finally, simulation results are provided to verify the effectiveness of the proposed control strategy.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"183 ","pages":"106952"},"PeriodicalIF":6.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142773950","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}

引用次数: 0

Lie group convolution neural networks with scale-rotation equivariance.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-28 DOI: 10.1016/j.neunet.2024.106980

Weidong Qiao, Yang Xu, Hui Li

{"title":"Lie group convolution neural networks with scale-rotation equivariance.","authors":"Weidong Qiao, Yang Xu, Hui Li","doi":"10.1016/j.neunet.2024.106980","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.106980","url":null,"abstract":"The weight-sharing mechanism of convolutional kernels ensures the translation equivariance of convolutional neural networks (CNNs) but not scale and rotation equivariance. This study proposes a SIM(2) Lie group-CNN, which can simultaneously keep scale, rotation, and translation equivariance for image classification tasks. The SIM(2) Lie group-CNN includes a lifting module, a series of group convolution modules, a global pooling layer, and a classification layer. The lifting module transfers the input image from Euclidean space to Lie group space, and the group convolution is parameterized through a fully connected network using the Lie Algebra coefficients of Lie group elements as inputs to achieve scale and rotation equivariance. It is worth noting that the mapping relationship between SIM(2) and its Lie Algebra and the distance measure of SIM(2) are defined explicitly in this paper, thus solving the problem of the metric of features on the space of SIM(2) Lie group, which contrasts with other Lie groups characterized by a single element, such as SO(2). The scale-rotation equivariance of Lie group-CNN is verified, and the best recognition accuracy is achieved on three categories of image datasets. Consequently, the SIM(2) Lie group-CNN can successfully extract geometric features and perform equivariant recognition on images with rotation and scale transformations.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"183 ","pages":"106980"},"PeriodicalIF":6.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142773953","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}

引用次数: 0

Generalization analysis of adversarial pairwise learning.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-28 DOI: 10.1016/j.neunet.2024.106955

Wen Wen, Han Li, Rui Wu, Lingjuan Wu, Hong Chen

引用次数: 0

Beyond homophily in spatial-temporal traffic flow forecasting.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-28 DOI: 10.1016/j.neunet.2024.106950

Yuxin Chen, Jingyi Huo, Fangru Lin, Hui Yan

{"title":"Beyond homophily in spatial-temporal traffic flow forecasting.","authors":"Yuxin Chen, Jingyi Huo, Fangru Lin, Hui Yan","doi":"10.1016/j.neunet.2024.106950","DOIUrl":"https://doi.org/10.1016/j.neunet.2024.106950","url":null,"abstract":"Traffic flow forecasting is a crucial yet complex task due to the intricate spatial-temporal correlations arising from road interactions. Recent methods model these interactions using message-passing Graph Convolution Networks (GCNs), which work for homophily graphs where connected nodes primarily exhibit close observations. However, relying solely on homophily graphs presents inherent limitations in traffic modeling, as road interactions can yield not only close but also distant observations over time, revealing diverse and dynamic node-wise correlations. We designate this phenomenon as homophily-heterophily dynamics, which has been largely overlooked in previous works. To address this gap, we propose a homophily-heterophily Spatial-Temporal Graph Convolution Network (H2STGCN) that exploits both homophily and heterophily components in the spatial-temporal domain. Specifically, we first adopt time-related node attributes to disentangle the diverse and dynamic node-wise relations across time, thereby obtaining homophily and heterophily Spatial-Temporal Graphs (STGs), which provide comprehensive insights into road interactions. Subsequently, we construct dual information propagation branches, each outfitted with a specific type of STG, to exploit multiple ranges of spatial-temporal correlations from distinct perspectives through dilated causal spatial-temporal graph convolution operations on STGs. Additionally, we introduce a Graph Collaborative Learning Module (GCLM) to capture the complementary information of these two branches via mutual information transfer. Experimental evaluation on four real-world traffic datasets reveals that our model outperforms state-of-the-art methods.","PeriodicalId":49763,"journal":{"name":"Neural Networks","volume":"183 ","pages":"106950"},"PeriodicalIF":6.0,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142792807","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}

引用次数: 0

Tensor ring rank determination using odd-dimensional unfolding.

IF 6 1区计算机科学

Neural Networks Pub Date : 2024-11-28 DOI: 10.1016/j.neunet.2024.106947

Yichun Qiu, Guoxu Zhou, Chao Li, Danilo Mandic, Qibin Zhao

引用次数: 0