• Home
  • Search
  • Neighborhood Pattern Is Crucial for Graph Convolutional Networks Performing Node Classification.
  • Cite Icon5
  • https://doi.org/10.1109/tnnls.2022.3229721Copy DOI Icon

Neighborhood Pattern Is Crucial for Graph Convolutional Networks Performing Node Classification.

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Graph convolutional networks (GCNs) are widely believed to perform well in the graph node classification task, and homophily assumption plays a core rule in the design of previous GCNs. However, some recent advances on this area have pointed out that homophily may not be a necessity for GCNs. For deeper analysis of the critical factor affecting the performance of GCNs, we first propose a metric, namely, neighborhood class consistency (NCC), to quantitatively characterize the neighborhood patterns of graph datasets. Experiments surprisingly illustrate that our NCC is a better indicator, in comparison to the widely used homophily metrics, to estimate GCN performance for node classification. Furthermore, we propose a topology augmentation graph convolutional network (TA-GCN) framework under the guidance of the NCC metric, which simultaneously learns an augmented graph topology with higher NCC score and a node classifier based on the augmented graph topology. Extensive experiments on six public benchmarks clearly show that the proposed TA-GCN derives ideal topology with higher NCC score given the original graph topology and raw features, and it achieves excellent performance for semi-supervised node classification in comparison to several state-of-the-art (SOTA) baseline algorithms.

Similar Papers
  • Research Article
  • Citations8

Entropy-aware self-training for graph convolutional networks

  • Aug 25, 2021
  • Neurocomputing
  • Gongpei Zhao +4
  • Book Chapter

Simplifying Graph Convolutional Networks as Matrix Factorization

  • Jan 01, 2021
  • Qiang Liu +2
  • Conference Article
  • Citations7

GCN-LRP explanation: exploring latent attention of graph convolutional networks

  • Jul 01, 2020
  • Jinlong Hu +2
  • PDF
  • Research Article
  • Citations5

Leveraging Graph Convolutional Networks for Semi-supervised Learning in Multi-view Non-graph Data

  • Mar 01, 2025
  • Cognitive Computation
  • F Dornaika +2
  • Book Chapter
  • Citations1

Self-attention Based Multi-scale Graph Convolutional Networks

  • Jan 01, 2023
  • Zhilong Xiong +1
  • Research Article
  • Citations45

GraphHop: An Enhanced Label Propagation Method for Node Classification.

  • Nov 01, 2023
  • IEEE Transactions on Neural Networks and Learning Systems
  • Tian Xie +2
  • Conference Article
  • Citations4

Cross-Space Adaptive Filter: Integrating Graph Topology and Node Attributes for Alleviating the Over-smoothing Problem

  • May 13, 2024
  • Chen Huang +4
  • PDF
  • Research Article
  • Citations14

Semi-Supervised Tree Species Classification for Multi-Source Remote Sensing Images Based on a Graph Convolutional Neural Network

  • Jun 11, 2023
  • Forests
  • Xueliang Wang +3
  • Research Article
  • Citations18

Dynamic Graph Learning Convolutional Networks for Semi-supervised Classification

  • Jan 31, 2021
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Sichao Fu +5
  • Research Article

IMG-80. Non-Invasive Classification of Glioblastoma Subtypes at the Infiltrative Tumor Margin Using Multiparametric MRI and Graph Convolutional Networks

  • Nov 11, 2025
  • Neuro-Oncology
  • Matthew Flick +17
  • Conference Article
  • Citations9

Lightweight Connectivity In Graph Convolutional Networks For Skeleton-Based Recognition

  • Sep 19, 2021
  • Hichem Sahbi
  • Research Article
  • Citations11

HDGCN: Dual-Channel Graph Convolutional Network With Higher-Order Information for Robust Feature Learning

  • Jan 01, 2024
  • IEEE Transactions on Emerging Topics in Computing
  • Meixia He +3
  • Research Article
  • Citations74

MDA-GCNFTG: identifying miRNA-disease associations based on graph convolutional networks via graph sampling through the feature and topology graph.

  • May 03, 2021
  • Briefings in bioinformatics
  • Yanyi Chu +10
  • Research Article
  • Citations32

Distributed Training of Graph Convolutional Networks

  • Dec 22, 2020
  • IEEE Transactions on Signal and Information Processing over Networks
  • Simone Scardapane +2
  • Book Chapter
  • Citations3

Detection of Discriminative Neurological Circuits Using Hierarchical Graph Convolutional Networks in fMRI Sequences

  • Jan 01, 2020
  • Xiaodan Xing +7
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.