• Home
  • Search
  • GraphHop: An Enhanced Label Propagation Method for Node Classification.
  • Open Access IconOpen Access
  • Cite Icon45
  • https://doi.org/10.1109/tnnls.2022.3157746Copy DOI Icon

GraphHop: An Enhanced Label Propagation Method for Node Classification.

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

A scalable semisupervised node classification method on graph-structured data, called GraphHop, is proposed in this work. The graph contains all nodes' attributes and link connections but labels of only a subset of nodes. Graph convolutional networks (GCNs) have provided superior performance in node label classification over the traditional label propagation (LP) methods for this problem. Nevertheless, current GCN algorithms suffer from a considerable amount of labels for training because of high model complexity or cannot be easily generalized to large-scale graphs due to the expensive cost of loading the entire graph and node embeddings. Besides, nonlinearity makes the optimization process a mystery. To this end, an enhanced LP method, called GraphHop, is proposed to tackle these problems. GraphHop can be viewed as a smoothening LP algorithm, in which each propagation alternates between two steps: label aggregation and label update. In the label aggregation step, multihop neighbor embeddings are aggregated to the center node. In the label update step, new embeddings are learned and predicted for each node based on aggregated results from the previous step. The two-step iteration improves the graph signal smoothening capacity. Furthermore, to encode attributes, links, and labels on graphs effectively under one framework, we adopt a two-stage training process, i.e., the initialization stage and the iteration stage. Thus, the smooth attribute information extracted from the initialization stage is consistently imposed in the propagation process in the iteration stage. Experimental results show that GraphHop outperforms state-of-the-art graph learning methods on a wide range of tasks in graphs of various sizes (e.g., multilabel and multiclass classification on citation networks, social graphs, and commodity consumption graphs).

Similar Papers
  • Research Article
  • Citations13

CLP-GCN: Confidence and label propagation applied to Graph Convolutional Networks

  • Nov 25, 2022
  • Applied Soft Computing
  • Mohadeseh Ghayekhloo +1
  • 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
  • Conference Article

WIFI fingerprint positioning algorithm based on location mapping in graph convolutional network

  • Nov 24, 2025
  • Hefei Liu +4
  • Research Article
  • Citations5

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

  • Jun 01, 2024
  • IEEE transactions on neural networks and learning systems
  • Gongpei Zhao +5
  • Conference Article
  • Citations7

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

  • Jul 01, 2020
  • Jinlong Hu +2
  • Conference Article
  • Citations49

Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation

  • Aug 14, 2021
  • Binghui Wang +3
  • Conference Article
  • Citations3

The Importance of Local Labels Distribution and Dominance for Node Classification in Graph Neural Networks

  • Dec 01, 2020
  • Asmaa Rassil +2
  • Research Article
  • Citations8

Annotation is easy: Learning to generate a shadow mask

  • Apr 14, 2022
  • Computers & Graphics
  • Xian-Tao Wu +3
  • Conference Article
  • Citations9

Semi-supervised Ensemble Learning Using Label Propagation

  • Oct 01, 2012
  • Hoyoung Woo +1
  • Research Article
  • Citations12

Cost-Sensitive Canonical Correlation Analysis for Semi-Supervised Multi-View Learning

  • Jan 01, 2020
  • IEEE Signal Processing Letters
  • Jianwu Wan +1
  • PDF
  • Conference Article
  • Citations46

MultiSage

  • Aug 20, 2020
  • Carl Yang +6
  • Conference Article
  • Citations321

Exploiting Edge Features for Graph Neural Networks

  • Jun 01, 2019
  • Liyu Gong +1
  • PDF
  • Research Article
  • Citations2

MulStepNET: stronger multi-step graph convolutional networks via multi-power adjacency matrix combination

  • Aug 06, 2021
  • Journal of Ambient Intelligence and Humanized Computing
  • Xun Liu +2
  • PDF
  • Research Article
  • Citations8

Enhanced Unsupervised Graph Embedding via Hierarchical Graph Convolution Network

  • Jul 26, 2020
  • Mathematical Problems in Engineering
  • H Zhang +2
  • Dissertation

Deep Learning on Graphs using Graph Convolutional Networks

  • May 22, 2019
  • Saurabh Mithe
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.