Scholarlink

<p>Graph neural networks (GNNs) have emerged as powerful tools for analyzing graph-structured data with applications in social networks, bioinformatics, and recommender systems. However, existing GNNs struggle with (1) rigid edge weighting (e.g., GCN’s fixed normalization), (2) over-smoothing in deep layers, and (3) quadratic attention costs (e.g., GAT). MGCN introduces: (1) adaptive edge weighting to dynamically adjust neighbor influence, (2) residual connections to combat over-smoothing, and (3) a scalable attention mechanism. It also introduces a standardized evaluation framework that incorporates adaptive preprocessing techniques such as feature normalization, edge weighting, and graph augmentation. The proposed model demonstrated superior performance when compared to eight state-of-the-art GNN models such as GraphSAGE, GAT, Graph Transformer, GINConv, GCN, GraphCL, AGCN, and MGCN, across three widely used benchmark datasets: Cora, CiteSeer, and PubMed. All evaluation metrics–including Accuracy, Hit Ratio, Precision, Recall, and F1 Score–are reported as the <Emphasis FontCategory="NonProportional">mean ± standard deviation</Emphasis> over 10 independent runs. The experimental results consistently demonstrate the superiority of the proposed MGCN model with approximately <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="11227_2025_7826_Article_IEq1.gif" Format="GIF" Height="16" Rendition="HTML" Resolution="72" Type="Linedraw" Width="23" /> </InlineMediaObject> <EquationSource Format="TEX">\(2\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mn>2</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation> improvement on above datasets.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Performance evaluation of diverse graph-based models on homogeneous datasets

  • 期刊论文

  • 发表日期：

    2025年9月15日

查看全文
  • Vinay Santhosh Chitla,
  • Hemantha Kumar Kalluri,
  • Satya Krishna Nunna

摘要

Graph neural networks (GNNs) have emerged as powerful tools for analyzing graph-structured data with applications in social networks, bioinformatics, and recommender systems. However, existing GNNs struggle with (1) rigid edge weighting (e.g., GCN’s fixed normalization), (2) over-smoothing in deep layers, and (3) quadratic attention costs (e.g., GAT). MGCN introduces: (1) adaptive edge weighting to dynamically adjust neighbor influence, (2) residual connections to combat over-smoothing, and (3) a scalable attention mechanism. It also introduces a standardized evaluation framework that incorporates adaptive preprocessing techniques such as feature normalization, edge weighting, and graph augmentation. The proposed model demonstrated superior performance when compared to eight state-of-the-art GNN models such as GraphSAGE, GAT, Graph Transformer, GINConv, GCN, GraphCL, AGCN, and MGCN, across three widely used benchmark datasets: Cora, CiteSeer, and PubMed. All evaluation metrics–including Accuracy, Hit Ratio, Precision, Recall, and F1 Score–are reported as the mean ± standard deviation over 10 independent runs. The experimental results consistently demonstrate the superiority of the proposed MGCN model with approximately \(2\%\) 2 % improvement on above datasets.