• Home
  • Search
  • MulStepNET: stronger multi-step graph convolutional networks via multi-power adjacency matrix combination
  • Cite Icon2
  • https://doi.org/10.1007/s12652-021-03355-xCopy DOI Icon

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

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

Graph convolutional networks (GCNs) have become the de facto approaches and achieved state-of-the-art results for circumventing many real-world problems on graph-structured data. However, these networks are usually shallow due to the over-smoothing of GCNs with many layers, which limits the expressive power of learning graph representations. The current methods of solving the limitations have the bottlenecks of high complexity and many parameters. Although Simple Graph Convolution (SGC) reduces the complexity and parameters, it fails to distinguish the feature information of neighboring nodes at different distances. To tackle the limits, we propose MulStepNET, a stronger multi-step graph convolutional network architecture, that can capture more global information, by simultaneously combining multi-step neighborhoods information. When compared to existing methods such as GCN and MixHop, MulStepNET aggregates neighborhoods information at more distant distances via multi-power adjacency matrix while fitting fewest parameters and being computationally more efficient. Experiments on citation networks including Pubmed, Cora, and Citeseer demonstrate that the proposed MulStepNET model improves over SGC by 2.8, 3.3, and 2.1% respectively while keeping similar stability, and achieves better performance in terms of accuracy and stability compared to other baselines.

Loading PDF

Similar Papers
  • Conference Article

An Efficient Recommendation Algorithm Integrating Knowledge Graph with Graph Convolutional Networks

  • Feb 01, 2023
  • Changzheng Xing +2
  • Research Article
  • Citations21

LightGCAN: A lightweight graph convolutional attention network for user preference modeling and personalized recommendation

  • Jun 09, 2023
  • Expert Systems with Applications
  • Ruiqin Wang +2
  • Conference Article
  • Citations3

Learning Graph Convolutional Networks based on Quantum Vertex Information Propagation (Extended Abstract)

  • May 01, 2022
  • Lu Bai +6
  • Research Article
  • Citations7

All-Cause Death Prediction Method for CHD Based on Graph Convolutional Networks

  • Jul 18, 2022
  • Computational Intelligence and Neuroscience
  • Yutao Xue +3
  • 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
  • Citations106

Co-Embedding of Nodes and Edges With Graph Neural Networks.

  • Oct 14, 2020
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • Xiaodong Jiang +3
  • Research Article
  • Citations20

Detecting anomalous traffic behaviors with seasonal deep Kalman filter graph convolutional neural networks

  • May 29, 2022
  • Journal of King Saud University - Computer and Information Sciences
  • Yanshen Sun +4
  • Research Article
  • Citations6

A U-Net Enhanced Graph Neural Network to Simulate Geological Carbon Sequestration

  • May 15, 2025
  • SPE Journal
  • Zeeshan Tariq +6
  • 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
  • PDF
  • Research Article
  • Citations9

Whole and Part Adaptive Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition.

  • Dec 13, 2020
  • Sensors
  • Qi Zuo +5
  • Research Article
  • Citations38

Cross-GCN: Enhancing Graph Convolutional Network with k-Order Feature Interactions

  • Jan 01, 2021
  • IEEE Transactions on Knowledge and Data Engineering
  • Fuli Feng +3
  • Research Article
  • Citations16

Boundary graph convolutional network for temporal action detection

  • Feb 20, 2021
  • Image and Vision Computing
  • Yaosen Chen +5
  • Conference Article
  • Citations1

A BERT-based Heterogeneous Graph Convolution Approach for Mining Organization-Related Topics

  • Jul 18, 2022
  • Haoda Qian +3
  • Research Article
  • Citations20

Integrating vertex and edge features with Graph Convolutional Networks for skeleton-based action recognition

  • Sep 20, 2021
  • Neurocomputing
  • Kai Liu +4
  • Research Article
  • Citations8

TCM syndrome classification using graph convolutional network

  • Aug 05, 2023
  • European Journal of Integrative Medicine
  • Shenghua Teng +4
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.