Higher-Order Graph Convolutional Networks With Multi-Scale Neighborhood Pooling for Semi-Supervised Node Classification

Graphs are data structures that effectively represent relational data in the real world. Graph representation learning is a significant task since it could facilitate various downstream tasks, such as node classification, link prediction, etc. Graph representation learning aims to map graph entities to low-dimensional vectors while preserving graph structure and entity relationships. Over the decades, many models have been proposed for graph representation learning. This paper aims to show a comprehensive picture of graph representation learning models, including traditional and state-of-the-art models on various graphs in different geometric spaces. First, we begin with five types of graph embedding models: graph kernels, matrix factorization models, shallow models, deep-learning models, and non-Euclidean models. In addition, we also discuss graph transformer models and Gaussian embedding models. Second, we present practical applications of graph embedding models, from constructing graphs for specific domains to applying models to solve tasks. Finally, we discuss challenges for existing models and future research directions in detail. As a result, this paper provides a structured overview of the diversity of graph embedding models.

show abstract

“…Graph Type Tasks Loss Function HCNP [217] Static graphs Node classification − ∑ v i ∈V y i log( ŷi ) CDMG [218] Static graphs Community detection…”

Section: Modelmentioning

confidence: 99%

Graph Representation Learning and Its Applications: A Survey

Hoang

Jeon

You

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Liu et al [20] suggest a different higher-order GCN with multi-scale community clustering to semi-supervised node labelling. MNPooling and high-order convolution are two primary categories.…”

Section: Node Classificationmentioning

confidence: 99%

“…NAGCN[13] Gong et al2019 Semi-supervised node categorisation works using the neighbourhood adaptive graph convolutional network D-SEGCN [15] Jia et al 2020 An attention method based on the deep hierarchical network for obtaining attribute dimensionsHCNP[20] …”

mentioning

confidence: 99%

Deep learning model construction for a semi-supervised classification with feature learning

Mandapati¹,

Kadry²,

Kumar

et al. 2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Several deep models were proposed in image processing, data interpretation, speech recognition, and video analysis. Most of these architectures need a massive proportion of training samples and use arbitrary configuration. This paper constructs a deep learning architecture with feature learning. Graph convolution networks (GCNs), semi-supervised learning and graph data representation, have become increasingly popular as cost-effective and efficient methods. Most existing merging node descriptions for node distribution on the graph use stabilised neighbourhood knowledge, typically requiring a significant amount of variables and a high degree of computational complexity. To address these concerns, this research presents DLM-SSC, a unique method semi-supervised node classification tasks that can combine knowledge from multiple neighbourhoods at the same time by integrating high-order convolution and feature learning. This paper employs two function learning techniques for reducing the number of parameters and hidden layers: modified marginal fisher analysis (MMFA) and kernel principal component analysis (KPCA). The MMFA and KPCA weight matrices are modified layer by layer when implementing the DLM, a supervised pretraining technique that doesn't require a lot of information. Free measuring on citation datasets (Citeseer, Pubmed, and Cora) and other data sets demonstrate that the suggested approaches outperform similar algorithms.

show abstract

“…Sun et al [19] proposes a multi-stage training algorithm framework based on self-training to classify node datasets with few labels. Liu et al [20] uses a high-order graph convolutional network to aggregate node information in different neighborhoods for node classification.…”

Section: Related Work a Graph Neural Networkmentioning

confidence: 99%

Hierarchical Structure-Feature Aware Graph Neural Network for Node Classification

et al. 2022

View full text Add to dashboard Cite

In recent years, graph neural network is used to process graph data and has been successfully applied to graph node classification task. Due to the complexity of graph structure and the difficulty of obtaining node labels, node classification in datasets with fewer labels becomes a challenge. Existing node classification problems with few-label nodes datasets usually use neighbor aggregation schemes. However, these methods lack the ''graph pooling mechanism,'' which makes these models impossible to make full use of the global graph information. To solve the problem, we propose a Hierarchical Structure-Feature aware Graph Neural Network (HSFGNN) model. The model learns node features by a hierarchical mechanism that repeatedly utilizes coarsening and refining methods at different levels. Firstly, we use topological information, node characteristics and connectivity of the graph to construct an intuitive and effective coarsening part based on multivariable analysis technology. Secondly, we aggregate the unselected nodes' features into the top-k nodes, so that the coarser nodes contain more abundant valid graph information. Finally, we propose an additional attention mechanism to obtain more accurate final representations of nodes. Experimental results show that the HSFGNN model achieves outstanding classification accuracy on the dataset with less labeled data.

show abstract

Higher-Order Graph Convolutional Networks With Multi-Scale Neighborhood Pooling for Semi-Supervised Node Classification

Cited by 11 publications

References 29 publications

Graph Representation Learning and Its Applications: A Survey

Graph Representation Learning and Its Applications: A Survey

Deep learning model construction for a semi-supervised classification with feature learning

Hierarchical Structure-Feature Aware Graph Neural Network for Node Classification

Contact Info

Product

Resources

About