检索结果-内蒙古大学图书馆

20th International Conference on Web Information Systems Engineering (WISE)

作者： Gao, Kaisheng Zhang, Jing Zhou, Cangqi Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China

ISBN: (纸本)9783030342234;9783030342227

The graph convolution network (GCN) is a widely-used facility to realize graph-based semi-supervised learning, which usually integrates node, features, and graph topologic information to build learning models. However, as for multi-label learning tasks, the supervision part of GCN simply minimizes the cross-entropy loss between the last layer outputs and the ground-truth label distribution, which tends to lose some useful information such as label correlations, so that prevents from obtaining high performance. In this paper, we propose a novel GCN-based semi-supervised learning approach for multi-label classification, namely ML-GCN. ML-GCN first uses a GCN to embed the node features and graph topologic information. Then, it randomly generates a label matrix, where each row (i.e., label vector) represents a kind of labels. The dimension of the label vector is the same as that of the node vector before the last convolution operation of GCN. That is, all labels and nodes are embedded in a uniform vector space. Finally, during the model training of ML-GCN, label vectors and node vectors are concatenated to serve as the inputs of the relaxed skip-gram model to detect the node-label correlation as well as the label-label correlation. Experimental results on several graph classification datasets show that the proposed ML-GCN outperforms four state-of-the-art methods.

关键词： graph convolution network graph embedding graph node classification Multi-label classification

来源：评论

学校读者我要写书评

暂无评论

Multi-label graph node classification with label attentive neighborhood convolution

引用

EXPERT SYSTEMS WITH APPLICATIONS 2021年 180卷 115063-115063页

作者： Zhou, Cangqi Chen, Hui Zhang, Jing Li, Qianmu Hu, Dianming Sheng, Victor S. Nanjing Univ Sci & Technol Sch Comp Sci & Engn Nanjing 210094 Peoples R China Wuyi Univ Intelligent Mfg Dept Jiangmen 529020 Peoples R China SenseDeal Intelligent Technol Co Ltd Beijing 100084 Peoples R China Texas Tech Univ Dept Comp Sci Lubbock TX 79409 USA

Learning with graph structured data is of great significance for many practical applications. A crucial and fundamental task in graph learning is node classification. In reality, graph nodes are often encoded with various attributes. In addition, the task is usually multi-labeled in nature. In this paper, we tackle the problem of multilabel graph node classification, by leveraging structure, attribute and label information simultaneously. Specifically, to obtain rational node feature representations, we propose an intuitive yet effective graph convolution module to aggregate local attribute information of a given node. Moreover, the homophily hypothesis motivates us to build a label attention module. By exploiting both input and output contextual representations, we utilize the additive attention mechanism and build a label-aware representation learning framework to measure the compatibility between pairs of node embeddings and label embeddings. The proposed novel neural networkbased, multi-label classification method has been verified by extensive experiments conducted on five publicavailable benchmark datasets, including both attributed and non-attributed networks. The results demonstrate the effectiveness of the proposed model with respect to micro-F1, macro-F1 and Hamming loss, comparing with several state-of-the-art methods, including two relational neighbor classifiers and several popular graph neural network models.

关键词： Multi-label classification graph node classification graph convolution Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised node classification via adaptive graph smoothing networks

引用

PATTERN RECOGNITION 2022年 124卷 108492-108492页

作者： Zheng, Ruigang Chen, Weifu Feng, Guocan Sun Yat Sen Univ Sch Math Guangzhou Peoples R China Sun Yat Sen Univ Guangdong Prov Key Lab Computat Sci Guangzhou Peoples R China

Inspections on current graph neural networks suggest us to reconsider the computational aspect of the final aggregation. We consider that such aggregations perform a prediction smoothing and impute their potential drawbacks to be the inter-class interference implied by the underlying graphs. We aim at weak-ening the inter-class connections so that aggregations focus more on intra-class relations and producing smooth predictions according to weakening results. We apply a metric learning module to learn new edge weights and combine entropy losses to ensure the correspondence between the predictions and the learnt distances so that the weights of inter-class edges are reduced and predictions are smoothed ac-cording to the modified graph. Experiments on four citation networks and a Wiki network show that in comparison with other state-of-the-art graph neural networks, the proposed algorithm can improve the classification accuracy. (c) 2021 Elsevier Ltd. All rights reserved.

关键词： Adaptive graph smoothing networks graph convolutional networks Semi-supervised learning graph node classification

来源：评论

学校读者我要写书评

暂无评论

SGB-Net: Scalable graph Broad Network

引用

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 2025年

作者： Xu, Yuebin Chen, C. L. Philip Wu, Mengqi Zhang, Tong South China Univ Technol Sch Comp Sci & Engn Guangzhou 510006 Peoples R China South China Univ Technol Guangdong Prov Key Lab Computat AI Models & Cognit Guangzhou 510006 Peoples R China Pazhou Lab Guangzhou 510335 Peoples R China Minist Educ Hlth Intelligent Percept & Paralleled Engn Res Ctr Guangzhou 510006 Peoples R China

Due to the complexity and self-evolutionary property of graph data in reality, graph learning methods require both validity to represent unstructured data and scalability to adapt to evolving graphs. However, current works have representation learning limitations on optimizable graph feature space due to the bottleneck of the structure depth. Moreover, they encounter a complete retraining process when graphs evolve, especially in the case without the assistance of new labels. To address the above issues, we propose a scalable graph broad network (SGB-Net), which contains three proposed modules: the graph feature broad transformation layer (GFBT layer) for enhancing graph embedding and two update algorithms (SGB-Net-U, SGB-Net-S) for endowing scalability. The GFBT layer aims to explicitly expand the graph feature space and broadly build the model. It constructs two expandable feature spaces in various graph scales to embed graphs discriminatively. SGB-Net-U is an exploratory method designed to tackle the label-free graph incremental learning (GIL) problem by leveraging unsupervised incremental knowledge to expand graph representation. SGB-Net-S endows scalability in classical incremental learning scenarios involving labels. Benefiting from its broad construction framework, SGB-Net not only enhances graph embeddings but also seamlessly adapts and improves performance in response to graph expansion without requiring retraining. In the experiments conducted on 15 benchmark datasets, SGB-Net outperforms state-of-the-art GNNs in terms of both effectiveness and scalability.

关键词： Scalability Representation learning Learning systems Feature extraction graph neural networks Incremental learning Optimization Training Message passing Electronic mail Broad learning system (BLS) graph neural network (GNN) graph node classification incremental learning system

来源：评论

学校读者我要写书评

暂无评论

AEGCN: An Autoencoder-Constrained graph Convolutional Network

引用

NEUROCOMPUTING 2021年 432卷 21-31页

作者： Ma, Mingyuan Na, Sen Wang, Hongyu Peking Univ Sch Elect Engn & Comp Sci Beijing Peoples R China Univ Chicago Dept Stat Chicago IL 60637 USA Coordinat Ctr China Natl Comp Network Emergency Response Tech Team Beijing Peoples R China

We propose a novel neural network architecture, called autoencoder-constrained graph convolutional network, to solve node classification task on graph domains. As suggested by its name, the core of this model is a convolutional network operating directly on graphs, whose hidden layers are constrained by an autoencoder. Comparing with vanilla graph convolutional networks, the autoencoder step is added to reduce the information loss brought by Laplacian smoothing. We consider applying our model on both homogeneous graphs and heterogeneous graphs. For homogeneous graphs, the autoencoder approximates to the adjacency matrix of the input graph by taking hidden layer representations as encoder and another one-layer graph convolutional network as decoder. For heterogeneous graphs, since there are multiple adjacency matrices corresponding to different types of edges, the autoencoder approximates to the feature matrix of the input graph instead, and changes the encoder to a particularly designed multi-channel pre-processing network with two layers. In both cases, the error occurred in the autoencoder approximation goes to the penalty term in the loss function. In extensive experiments on citation networks and other heterogeneous graphs, we demonstrate that adding autoencoder constraints significantly improves the performance of graph convolutional networks. Further, we notice that our technique can be applied on graph attention network to improve the performance as well. This reveals the wide applicability of the proposed autoencoder technique. (c) 2020 Elsevier B.V. All rights reserved.

关键词： Homogeneous and heterogeneous graphs graph convolutional networks graph autoencoder graph node classification

来源：评论

学校读者我要写书评

暂无评论

Information-Enhanced graph Neural Network for Transcending Homophily Barriers

引用

IEEE ACCESS 2024年 12卷 194804-194815页

作者： Liu, Xiao Zhang, Lijun Guan, Hui Univ Massachusetts Amherst Coll Informat & Comp Sci Amherst MA 01002 USA

Homophily and heterophily are intrinsic properties of graphs that describe whether linked nodes share similar properties. While Message Passing Neural Networks (MPNNs) have shown remarkable success in node classification tasks, their performance often deteriorates within specific homophily ranges, which we term the gray area. In this work, we identify and theoretically demonstrate the challenges faced by MPNNs in this gray area, highlighting the limitations of existing approaches in addressing it. To overcome these limitations, we propose the INformation-enhanced graph Neural Network (INGNN), which introduces a novel framework that integrates three complementary features-ego-node features, graph structure features, and aggregated neighborhood features-through an adaptive feature fusion mechanism based on bi-level optimization. This design enables INGNN to transcend the homophily barriers and generalize effectively across the entire homophily spectrum. We validate the effectiveness of INGNN through extensive experiments on both synthetic and real-world datasets with different graph homophily. Specifically, INGNN outperforms 12 state-of-the-art MPNNs with an average rank of 1.78 on 9 real node classification datasets. Our ablation studies further show experimental evidence of how the integrated features contribute to the model's performance under different homophily settings. INGNN is open-sourced and available at https://***/xl1990/ingnn.

关键词： Feature extraction graph neural networks Accuracy Vectors Transforms Hands Ash Aggregates Systematics Stacking graph neural networks (GNNs) graph homophily graph node classification

来源：评论

学校读者我要写书评

暂无评论

DE-GCN: Differential Evolution as an optimization algorithm for graph Convolutional Networks 26

DE-GCN: Differential Evolution as an optimization algorithm ...

引用

26th International Computer Conference of the Computer-Society-of-Iran

作者： Tasharrofi, Shakiba Taheri, Hassan Amirkabir Univ Technol Elect Engn Dept Digital Elect Syst Tehran Iran Amirkabir Univ Technol Elect Engn Dept Tehran Iran

ISBN: (纸本)9781665412414

Neural networks had impressive results in recent years. Although neural networks only performed using Euclidean data in past decades, many data-sets in the real world have graph structures. This gap led researchers to implement deep learning on graphs. The graph convolutional network (GCN) is one of the graph neural networks. We propose the differential evolutional optimization method as an optimizer for GCN instead of gradient-based methods in this work. Hence the differential evolution algorithm applies for graph convolutional network's training and parameter optimization. The node classification task is a non-convex problem. Therefore DE algorithm is suitable for these kinds of complex problems. Implementing evolutionally algorithms on GCN and parameter optimization are explained and compared with traditional GCN. DE-GCN outperforms and improves the results by powerful local and global searches. It also decreases the training time.

关键词： graph convolutional network graph node classification Neuroevolution Differential evolution algorithm Anomaly Detection

来源：评论

学校读者我要写书评

暂无评论

An Aggressive graph-based Selective Sampling Algorithm for classification 15

An Aggressive Graph-based Selective Sampling Algorithm for C...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yang, Peng Zhao, Peilin Zheng, Vincent W. Li, Xiao-Li ASTAR Inst Infocomm Res Singapore 138632 Singapore UIUC Adv Digital Sci Ctr Singapore 138632 Singapore

ISBN: (纸本)9781467395038

Traditional online learning algorithms are designed for vector data only, which assume that the labels of all the training examples are provided. In this paper, we study graph classification where only limited nodes are chosen for labelling by selective sampling. Particularly, we first adapt a spectral-based graph regularization technique to derive a novel online learning linear algorithm which can handle graph data, although it still queries the labels of all nodes and thus is not preferred, as labelling is typically time-consuming. To address this issue, we then propose a new confidence-based query method for selective sampling. The theoretical result shows that our online learning algorithm with a fraction of queried labels can achieve a mistake bound comparable with the one learning on all labels of the nodes. In addition, the algorithm based on our proposed query strategy can achieve a mistake bound better than the one based on other query methods. However, our algorithm is conservative to update the model whenever error happens, which obviously wastes training labels that are valuable for the model. To take advantage of these labels, we further propose a novel aggressive algorithm, which can update the model aggressively even if no error occurs. The theoretical analysis shows that our aggressive approach can achieve a mistake bound better than its conservative and fully-supervised counterpart, with substantially fewer queried times. We empirically evaluate our algorithm on several real-world graph datasets and the experimental results demonstrate that our method is highly effective.

关键词： Online Learning Selective Sampling graph node classification

来源：评论

学校读者我要写书评

暂无评论

DYNAMIC graph CONVOLUTIONAL NETWORK: A TOPOLOGY OPTIMIZATION PERSPECTIVE 31

DYNAMIC GRAPH CONVOLUTIONAL NETWORK: A TOPOLOGY OPTIMIZATION...

引用

IEEE 31st International Workshop on Machine Learning for Signal Processing (MLSP)

作者： Deng, Bowen Jiang, Aimin Hohai Univ Coll Internet Things Engn Changzhou Peoples R China

ISBN: (纸本)9781728163383

Recently, graph convolutional networks(GCNs) have drawn increasing attention in many domains, e.g., social networks, recommendation systems. It's known that, in the task of graph node classification, inter-class edges connecting nodes from different categories often degrade the GCN model performance. On the other hand, a stronger intra-class connection in terms of the edge number and edge weights is always beneficial to node classification. Most existing GCN models assume that the topology and edge weights of the underlying graph are both fixed. However, real-world networks are often noisy and incomplete. To take into account such uncertainty in graph topology, we propose in this paper a dynamic graph convolution network (DyGCN), where edge weights are treated as learnable parameters. A novel adaptive edge dropping (AdaDrop) strategy is developed for DyGCN, such that even graph topology can be optimized. DyGCN is also a flexible architecture that can be readily combined with other deep GCN models to cope with the oversmoothness encountered when the network goes very deep. Experimental results demonstrate that the proposed DyGCN and its deep variants can achieve competitive classification accuracy in many datasets.

关键词： graph deep learning supervised learning graph node classification graph topology optimization

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous graph Attribute Completion via Efficient Meta-path Context-Aware Learning 6th

Heterogeneous Graph Attribute Completion via Efficient Meta-...

引用

6th Chinese Conference on Pattern Recognition and Computer Vision (PRCV)

作者： Zhang, Lijun Chen, Geng Wang, Qingyue Wang, Peng Northwestern Polytech Univ Sch Comp Sci Xian Peoples R China Northwestern Polytech Univ Ningbo Inst Xian Peoples R China

ISBN: (纸本)9789819985456;9789819985463

Heterogeneous graph attribute completion (HGAC) is an emerging research direction and has drawn increasing research attention in recent years. Although making significant progress, existing HGAC methods suffer from three limitations, including (i) the ignorance of valuable meta-path information during the graph node encoding, (ii) insufficient graph context learning as only neighboring nodes are considered during the completion process, and (iii) low efficiency due to the use of heterogeneous graph neural network for downstream tasks. To address these limitations, we propose an efficient meta-path context-aware learning framework to improve the completion of missing attributes of heterogeneous graphs. In our framework, we introduce a collaborative metapath-driven embedding scheme, which incorporates valuable meta-path prior knowledge during node sampling. Furthermore, we devise a contextaware attention mechanism to complete the missing node attributes, which captures the information of non-neighbor nodes. Finally, we adopt graph attention networks for downstream tasks, effectively improving computational efficiency. Extensive experiments on three real-world heterogeneous graph datasets demonstrate that our framework outperforms state-of-the-art HGAC methods remarkably.

关键词： graph neural networks Attribute completion Heterogeneous graph learning graph node classification

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：