Complex & Intelligent Systems最新文献_第10页

RT-GPNet: a cascaded contextual encoding and rotary position-aware framework for named entity recognition in Chinese emergency texts RT-GPNet：用于中文紧急文本命名实体识别的级联上下文编码和旋转位置感知框架

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-13 DOI: 10.1007/s40747-026-02399-w

Nietong Wang, Yinhua Tian, Fangyu Cheng, Cong Liu

引用次数: 0

Privacy-preserving communication compression and robust aggregation for hierarchical federated learning 面向分层联邦学习的保密通信压缩和鲁棒聚合

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-13 DOI: 10.1007/s40747-026-02465-3

Senyu Bao, Shuhui Wu, Badreddine Tanane, Yuanhong Tao

引用次数: 0

Research on segmentation technology of transmission lines based on aerial images 基于航拍图像的输电线路分割技术研究

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-12 DOI: 10.1007/s40747-026-02376-3

Yiteng Jin, Min He, Gujing Han, Liang Qin, Kaipei Liu

引用次数: 0

Exploring data sparsity correlation: boosting DNN training on the edge via sparsity modeling 探索数据稀疏性相关性：通过稀疏性建模在边缘上增强DNN训练

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-11 DOI: 10.1007/s40747-026-02426-w

Miao Wang, Shengbing Zhang, Chuxi Li, Zhao Yang, Meng Zhang

引用次数: 0

IHFD: an improved heartbeat-based failure detector of $$Diamond ,P$$ class for partially synchronous hierarchical distributed systems IHFD：一个改进的基于心跳的故障检测器$$Diamond ,P$$类，用于部分同步的分层分布式系统

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-09 DOI: 10.1007/s40747-026-02423-z

Bhavana Chaurasia, Anshul Verma, Pradeepika Verma

引用次数: 0

LeaDeiT: data-efficient image transformer with knowledge distillation for leather species identification 基于知识蒸馏的皮革品种识别数据高效图像转换器

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-08 DOI: 10.1007/s40747-026-02431-z

S. Sundar Rajan, Atharv Barai, Malathy Jawahar, A. Amalin Prince

引用次数: 0

ChiralFusion: correcting distributional and perceptual asymmetries in multi-modal 3D object detection via density-position chirality ChiralFusion：通过密度-位置手性校正多模态3D物体检测中的分布和感知不对称

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-07 DOI: 10.1007/s40747-026-02458-2

Wenyu Ji, Yang Li, Jiabao Wang, Wei Bai, Zhuang Miao

引用次数: 0

Broad graph convolutional network: a novel graph convolutional network paradigm without hidden layer 广义图卷积网络：一种新的无隐藏层的图卷积网络范式

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-07 DOI: 10.1007/s40747-026-02435-9

Alex Hay-Man Ng, Xun Liu, Fangyuan Lei, Xuejiao Liao, Lei Zhang, Jinchang Ren

{"title":"Broad graph convolutional network: a novel graph convolutional network paradigm without hidden layer","authors":"Alex Hay-Man Ng, Xun Liu, Fangyuan Lei, Xuejiao Liao, Lei Zhang, Jinchang Ren","doi":"10.1007/s40747-026-02435-9","DOIUrl":"https://doi.org/10.1007/s40747-026-02435-9","url":null,"abstract":"Graph convolutional networks (GCNs) have shown promising performance in real-world applications involving graph-structured data. To enhance the model’s ability to integrate information from neighbor nodes, GCNs typically expand the receptive field by stacking more layers, which can lead to the problem of over-smoothing. To address this limitation, high-order graph convolutional networks (HGCNs) such as Mixhop have been proposed. These high-order models, however, introduce the risk of overfitting due to the increased number of parameters required for designing different order convolutions, which in turn can degrade classification performance. To overcome these issues, we first provide a theoretical analysis of the bottlenecks in conventional GCNs and establish that an effective graph convolutional model should integrate multi-hop neighborhood information in a unified manner. Inspired by this, we propose a novel broad graph convolutional network (BGCN) paradigm, which completely eliminates hidden layers and instead expands the receptive field through network width. We introduce four specific BGCN architectures and provide a detailed analysis of their computational complexity and parameter efficiency. A number of experiments on citation networks demonstrate that the proposed methods achieve state-of-the-art performance in terms of both classification accuracy and stability. In particular, our BGCN with simple attention mechanism ( $$text {BGCN}_{text {SA}}$$ <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"> <mml:msub> <mml:mtext>BGCN</mml:mtext> <mml:mtext>SA</mml:mtext> </mml:msub> </mml:math> ) achieves top performance on the Citeseer, Cora, and Pubmed datasets, with accuracies of 73.3%, 83.5%, and 81.1%, respectively. The main advantage of this work lies in offering a robust, efficient, and scalable alternative for graph representation learning, effectively circumventing the inherent limitations of over-smoothing and overfitting in existing deep and high-order GCN models.","PeriodicalId":10524,"journal":{"name":"Complex & Intelligent Systems","volume":"452 1","pages":""},"PeriodicalIF":5.8,"publicationDate":"2026-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148690803","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

MF-DETR: an efficient end-to-end framework for small object detection in UAV imagery MF-DETR：一种高效的端到端无人机图像小目标检测框架

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-07 DOI: 10.1007/s40747-026-02459-1

Qilie Liu, Chuanjun Zhou, Junxi Liu, Yang Fang, Yu Tao, Yongju Xian

引用次数: 0

Modality-task dependent heterogeneous mixture-of-experts model for multimodal time series representation learning 基于模态任务的多模态时间序列表示学习异构混合专家模型

IF 5.8 2区计算机科学

Complex & Intelligent Systems Pub Date : 2026-08-06 DOI: 10.1007/s40747-026-02448-4

Lei Yao, Yong Zhang, Qin Li, Qi Li, Zhenyu Zhang, Zhongxu Si, Jiawei Chen

引用次数: 0