Neurocomputing最新文献_第8页

An 80/20 cortical balance stabilizes information-rich dynamics 80/20的皮质平衡稳定了信息丰富的动态

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-24 DOI: 10.1016/j.neucom.2025.131651

Mozhgan Khanjanianpak , Maryam Pakpour , Matjaž Perc , Alireza Valizadeh

引用次数: 0

Explaining and interpreting hyperdimensional computing classifiers on tabular data 解释和解释表格数据上的超维计算分类器

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-24 DOI: 10.1016/j.neucom.2025.131643

Laura Smets , Werner Van Leekwijck , Steven Latré , José Oramas

引用次数: 0

Grade: Generative graph contrastive learning for multimodal recommendation 等级：多模式推荐的生成图对比学习

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-24 DOI: 10.1016/j.neucom.2025.131630

Yu-Chao Ping , Shu-Qin Wang , Zi-Yi Yang , Yong-Quan Dong , Meng-Xiang Hu , Pei-Lin Zhang

{"title":"Grade: Generative graph contrastive learning for multimodal recommendation","authors":"Yu-Chao Ping , Shu-Qin Wang , Zi-Yi Yang , Yong-Quan Dong , Meng-Xiang Hu , Pei-Lin Zhang","doi":"10.1016/j.neucom.2025.131630","DOIUrl":"10.1016/j.neucom.2025.131630","url":null,"abstract":"<div><div>Multimodal recommender systems based on graph convolutional networks have made significant progress by integrating multiple modal data for item recommendation. While most existing approaches learn user and item representations through modality-related interaction graphs, these approaches still encounter challenges inherent to graph convolutional networks: over-smoothing. To address this challenge, we propose a model named Grade, <u>G</u>enerative G<u>r</u>aph Contr<u>a</u>stive Learning for Multimo<u>d</u>al R<u>e</u>commendations. It combines generative models and contrastive learning and design four task losses. In particular, the generative graph contrastive task generates contrastive views inter-modal through variational graph reconstruction, effectively aligning modal features to improve user and item representations. In addition, the feature perturbation contrastive task generates multimodal noisy views with interference for intra-modal contrast through noise-based self-supervised learning, effectively enhancing the robustness of modality-specific representations. Finally, we incorporate the Variational Graph Autoencoders (VGAE) task and the Bayesian Personalized Ranking (BPR) task. The combination of these four task losses effectively mitigates the issues of over-smoothing. Extensive experiments conducted on three publicly available datasets confirm the superiority of our model. The related code is available on <span><span>https://github.com/Ricardo-Ping/Grade</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"657 ","pages":"Article 131630"},"PeriodicalIF":6.5,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145156971","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Connected multi-hierarchies lightweight global hierarchical model in hyper-relational knowledge graphs 超关系知识图中的连接多层次轻量级全局层次模型

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-23 DOI: 10.1016/j.neucom.2025.131641

Jiahang Li, Qilong Han, Hui Zhang, Lijie Li, Dan Lu

{"title":"Connected multi-hierarchies lightweight global hierarchical model in hyper-relational knowledge graphs","authors":"Jiahang Li, Qilong Han, Hui Zhang, Lijie Li, Dan Lu","doi":"10.1016/j.neucom.2025.131641","DOIUrl":"10.1016/j.neucom.2025.131641","url":null,"abstract":"<div><div>Hyper-relational knowledge graphs enriched by qualifiers have wide applications across diverse fields, and knowledge representation learning is emerging as a prominent research focus. Existing representation methods primarily concentrate on the local hierarchies of each element, overlooking the global hierarchies and their complex dependencies which can result in substantial semantic incompleteness and degraded model generalization. While modeling global hierarchical semantics presents a challenge, integrating local and global hierarchies further increases computational complexity. To tackle these challenges, we propose CMLG, a lightweight global hierarchical representation learning method that connects multiple hierarchies and leverages varied hierarchical details to improve learning effectiveness. Specifically, interactions within local hierarchies are utilized to update the local vectors of triples and qualifiers, thereby capturing essential semantic aggregations at the local hierarchies to construct global hierarchical expressions of entities and relations. These global representations encompass the essential features of hyper-relational facts and are utilized for computational tasks across various domains. To enhance the quality of embeddings, contrastive methods that connect multi-hierarchies are utilized within and across these hierarchies to boost the model’s learning capabilities. Considering the computational resources required for learning at both local and global hierarchies, CMLG adopts the lightweight design to reduce the parameters and computational demands of training, thereby enhancing its suitability for large-scale datasets. Comprehensive experiments on various datasets reveal that our approach outperforms advanced models, achieving up to a 12 % improvement in MRR over the runner-ups.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"657 ","pages":"Article 131641"},"PeriodicalIF":6.5,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222618","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Sensitivity-propagated dual-frequency graph neural network for multivariate time series forecasting 多变量时间序列预测的灵敏度传播双频图神经网络

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-23 DOI: 10.1016/j.neucom.2025.131644

Yaling Xun , Shuo Han , Jianghui Cai , Haifeng Yang , Jifu Zhang

{"title":"Sensitivity-propagated dual-frequency graph neural network for multivariate time series forecasting","authors":"Yaling Xun , Shuo Han , Jianghui Cai , Haifeng Yang , Jifu Zhang","doi":"10.1016/j.neucom.2025.131644","DOIUrl":"10.1016/j.neucom.2025.131644","url":null,"abstract":"<div><div>Graph Neural Networks (GNNs) have become one of the mainstream frameworks in multivariate time series (MTS) forecasting due to their powerful spatio-temporal dependency modeling capability. The process of extracting spatio-temporal features can be summarized into three stages: graph generation, graph convolution, and node updating. However, existing works recognize that the quality of the generated graph significantly impacts model performance, while overlooking that effective node updating can produce richer series representations. Furthermore, existing GNNs exhibit a pronounced bias toward capturing low-frequency temporal patterns, with inadequate attention to high-frequency components. Therefore, we propose SensGCN, a novel dynamic graph spatio-temporal network by introducing the concept of series sensitivity features to optimize the node updating process. Built upon a graph convolutional Gated Recurrent Unit (GRU) framework, SensGCN derives sensitivity features from series volatility patterns under non-autocorrelation conditions. These features subsequently guide node updating after aggregating external series information through graph convolution. Additionally, a novel dynamic graph estimation method is developed that extracts high-frequency components via series decomposition to jointly model time-varying spatial dependencies in MTS data, thereby enhancing GNNs’ capability in learning high-frequency features. Extensive evaluations across five public datasets show that our SensGCN achieves competitive or state-of-the-art performance in both multi-step and single-step forecasting tasks. Notably, in multi-step forecasting with a predefined graph structure, SensGCN achieves the best performance in four out of six cases and consistently attains the lowest MAE, outperforming the best baselines by up to approximately 1.3 %.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"657 ","pages":"Article 131644"},"PeriodicalIF":6.5,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223202","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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-view least squares support vector classifiers with the principles of complementarity and consensus 基于互补和一致性原则的多视图最小二乘支持向量分类器

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-23 DOI: 10.1016/j.neucom.2025.131647

Siyuan Zhang , Qianfei Liu , Mengyang Fan , Weisong Mu , Jianying Feng

{"title":"Multi-view least squares support vector classifiers with the principles of complementarity and consensus","authors":"Siyuan Zhang , Qianfei Liu , Mengyang Fan , Weisong Mu , Jianying Feng","doi":"10.1016/j.neucom.2025.131647","DOIUrl":"10.1016/j.neucom.2025.131647","url":null,"abstract":"<div><div>In this paper, we examine the multi-view learning framework, which adheres to the principles of complementarity and consensus. Despite significant advances in various support vector machine (SVM)-based multi-view learning methods, many focus exclusively on one of these principles. To bridge this gap, we first introduce the multi-view least squares support vector classifier (MvLSSVC-2C), which effectively minimizes the squares of the differences in decision functions across diverse views while also integrating information from multiple views through a coupling term. Furthermore, we propose a structural information-based model, termed SMvLSSVC-2C, which leverages hierarchical agglomerative clustering to enhance information exchange among views, thereby promoting complementarity and consensus. Meanwhile, by incorporating a weight allocation strategy, adaptive learning is conducted, and the importance of each view is adjusted to adhere to the principle of complementarity. We adopt the alternating optimization method to solve it. The two proposed methods exhibit superior performance, which is demonstrated by theoretical and numerical analysis. Our experimental results demonstrate the effectiveness of the proposed models on diverse datasets, highlighting their enhanced performance in multi-view learning tasks.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"657 ","pages":"Article 131647"},"PeriodicalIF":6.5,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145223330","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

ADMS-LSTM: A multi-scale stacked LSTMs long-term prediction method based on an adaptive decomposition framework with DFT-AutoCorrelation ADMS-LSTM：一种基于dft自相关自适应分解框架的多尺度叠加lstm长期预测方法

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-23 DOI: 10.1016/j.neucom.2025.131362

Jinqi Zhao , Haomiao Shang

{"title":"ADMS-LSTM: A multi-scale stacked LSTMs long-term prediction method based on an adaptive decomposition framework with DFT-AutoCorrelation","authors":"Jinqi Zhao , Haomiao Shang","doi":"10.1016/j.neucom.2025.131362","DOIUrl":"10.1016/j.neucom.2025.131362","url":null,"abstract":"<div><div>Effective long-term forecasting can provide valuable decision-making information and demonstrate significant application value. Because of the difficulty of learning complex time patterns and the accumulation of prediction errors, the current research on long-term forecasting is still limited. In this paper, to capture multi-scale long-term dependencies, a novel framework Discrete Fourier Transform (DFT)-AutoCorrelation Pyramid Decomposition LSTM (ADMS-LSTM) is proposed. ADMS-LSTM mainly includes an adaptive decomposition window analysis module, a pyramid decomposition module, and a prediction-fusion module. First, the adaptive decomposition window analysis module based on DFT and the AutoCorrelation mechanism is designed to select the optimal decomposition window adaptively and provide a reliable theoretical basis for the pyramid decomposition module. Furthermore, multi-scaled information from the pyramid decomposition module is beneficial for mining distant historical dependencies. Finally, in the prediction-fusion module, the complex time patterns are learned and multi-scaled prediction series are fused, to improve the local prediction information and solve the problem of prediction error accumulation. To verify the effectiveness and robustness of the proposed method, six publicly available benchmark datasets are chosen for our experiment. Comparative experimental results show that our proposed method achieves state-of-the-art performance on these datasets compared with other latest methods. The proposed method can effectively alleviate the problem of error accumulation, extract the long-term temporal characteristics, and obtain excellent long-term prediction results. To the best of our knowledge, this is the first work based on rigorous mathematical theory to adaptively select decomposition windows for long-sequence information learning.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"657 ","pages":"Article 131362"},"PeriodicalIF":6.5,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145269559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

Dual perspective-aware graph neural network for graph-level anomaly detection 面向图级异常检测的双视角感知图神经网络

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-23 DOI: 10.1016/j.neucom.2025.131649

Jianliang Gao , Xinqiu Zhang , Qiutong Li , Jiamin Chen

{"title":"Dual perspective-aware graph neural network for graph-level anomaly detection","authors":"Jianliang Gao , Xinqiu Zhang , Qiutong Li , Jiamin Chen","doi":"10.1016/j.neucom.2025.131649","DOIUrl":"10.1016/j.neucom.2025.131649","url":null,"abstract":"<div><div>Graph-level anomaly detection based on graph neural networks (GAD-GNN) aims to identify graphs exhibiting anomalous characteristics distinct from the majority in a dataset. However, existing GAD-GNN methods face two critical challenges: Aggregation anomaly dilution occurs when the signals of sparsely distributed abnormal nodes are overwhelmed by the dominant influence of normal nodes during message passing. Readout anomaly dilution arises when locally concentrated anomalies are smoothed out in graph readout. To overcome these challenges, we propose the <strong>D</strong>ual <strong>P</strong>erspective-Aware <strong>G</strong>raph <strong>N</strong>eural <strong>N</strong>etwork (DPGNN), which integrates two complementary modules. The Global Awareness Module enhances node representations with multi-scale return-probability fingerprints, ensuring that signals of sparsely distributed abnormal nodes are preserved against overwhelming normal patterns. The Local Awareness Module adaptively identifies anomaly subgraphs using structural cues and employs attention-based readout to retain concentrated anomalies from being diluted in graph readout. Extensive experiments on multiple benchmark datasets demonstrate that DPGNN consistently outperforms state-of-the-art methods, validating its effectiveness in detecting graph-level anomalies.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"658 ","pages":"Article 131649"},"PeriodicalIF":6.5,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145236198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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

MAGNet: A multimodal knowledge-augmented graph network for early-stage misinformation detection MAGNet：一种用于早期错误信息检测的多模态知识增强图网络

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-23 DOI: 10.1016/j.neucom.2025.131533

Wang Jinghong , Yang Hongbo , Wang Xizhao , Wang Wei , Li Yanan

{"title":"MAGNet: A multimodal knowledge-augmented graph network for early-stage misinformation detection","authors":"Wang Jinghong , Yang Hongbo , Wang Xizhao , Wang Wei , Li Yanan","doi":"10.1016/j.neucom.2025.131533","DOIUrl":"10.1016/j.neucom.2025.131533","url":null,"abstract":"<div><div>With the rapid proliferation of multimodal misinformation on social media, detecting such content has become increasingly challenging. Existing approaches often rely on flat or shallow fusion strategies, which fail to capture structured semantic interactions across modalities. Moreover, most methods lack controllable, task-relevant mechanisms for integrating external knowledge, limiting their adaptability to emerging misinformation. In this paper, we present MAGNet, a Multimodal Augmented Graph Network that models fine-grained features with LLM-enhanced contextual knowledge through a hierarchical graph attention framework. MAGNet constructs heterogeneous graphs with modality- and context-specific edge weights based on semantic and affective alignment, enabling progressive reasoning from local features to global representations. Extensive experiments on three real-world datasets demonstrate that MAGNet consistently outperforms strong baselines across multiple evaluation metrics. The results underscore the effectiveness of combining graph-based modeling, fine-grained fusion, and structured knowledge integration in developing scalable and robust solutions for multimodal misinformation detection.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"658 ","pages":"Article 131533"},"PeriodicalIF":6.5,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145271184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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-label webpage text classification based on feature segmentation and attention mechanism 基于特征分割和注意机制的多标签网页文本分类

IF 6.5 2区计算机科学

Neurocomputing Pub Date : 2025-09-23 DOI: 10.1016/j.neucom.2025.131635

Yanan Cheng, Wenling Li, Zhichao Zhang, Hao Chen, Zhaoxin Zhang

{"title":"Multi-label webpage text classification based on feature segmentation and attention mechanism","authors":"Yanan Cheng, Wenling Li, Zhichao Zhang, Hao Chen, Zhaoxin Zhang","doi":"10.1016/j.neucom.2025.131635","DOIUrl":"10.1016/j.neucom.2025.131635","url":null,"abstract":"<div><div>Due to the natural distribution differences of webpage content, multi-label webpage text datasets suffer from the long-tailed label problem. Moreover, the length of multi-label webpage text varies, making it difficult for sequence based deep learning models to set the sequence length. In order to solve the above problems, a feature self segmentation strategy is proposed in this paper, which executes different segmentation strategies for webpage texts of different lengths based on the sequence length of the deep learning model, so as to preserve long webpage texts without introducing too much noisy data for short webpage texts. In addition, by calculating the attention of adjacent segments, calculating the attention of labels and different segments, and constructing the co-attention networks, not only can important content in the document be highlighted, but also content related to labels can be highlighted, which can effectively extract features associated with low-frequency labels and solve the long-tailed label problem. The comparative experimental results on the manually annotated Energy Website Multi-Label Webpage Text dataset and three benchmark multi-label text classification datasets demonstrate that the method constructed in this paper outperforms all baseline methods. The main codes are available at <span><span>https://github.com/sgysgywaityou/MLWT-FSAM/tree/main/MLWT-FSAM</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"657 ","pages":"Article 131635"},"PeriodicalIF":6.5,"publicationDate":"2025-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145222625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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