Semi-Supervised Classification with Graph Convolutional Networks
Полуобучаемая классификация с использованием графовых сверточных сетей
2016-09-09
SCID: 54.1/jzvq99zh
Discuss with AI
citation networksgraph convolutional networksknowledge graphsemi-supervised classificationspectral graph convolutions
Figures from the paper
Abstract (AI)
We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes. In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.
Key Findings
1
Derives the convolutional architecture from a localized first-order approximation of spectral graph convolutions.
2
Experiments on citation networks and a knowledge graph show significant performance improvements over related methods.
3
Introduces a scalable semi-supervised learning approach using graph convolutional networks that operate directly on graph-structured data.
4
The model scales linearly with the number of graph edges while encoding local graph structure and node features in hidden representations.
Research Object
Graph-structured data, including citation networks and a knowledge graph
Research Subject
Semi-supervised node classification using graph convolutional networks that learn representations from local graph structure and node features
Publication Details
Publication Date
2016-09-09
Journal
Publisher
ISSN
Cited by
35372
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai3
Cited by20
A Comprehensive Survey on Graph Neural Networks2020
Graph neural networks: A review of methods and applications2020
Dynamic Graph CNN for Learning on Point Clouds2019
A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects2021
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting2018
Attention Based Spatial-Temporal Graph Convolutional Networks for Traffic Flow Forecasting2019
Graph Convolutional Neural Networks for Web-Scale Recommender Systems2018
A Survey on Knowledge Graphs: Representation, Acquisition, and Applications2021
Heterogeneous Graph Attention Network2019
Recent advances and applications of machine learning in solid-state materials science2019
A survey on semi-supervised learning2019
Convolutional 2D Knowledge Graph Embeddings2018
Heterogeneous Graph Transformer2020
Knowledge Graphs2021
Graph convolutional networks: a comprehensive review2019
The rise of deep learning in drug discovery2018
Deep Learning on Graphs: A Survey2020
Graph Convolutional Networks for Hyperspectral Image Classification2020
Graph Neural Network-Based Anomaly Detection in Multivariate Time Series2021
Graph Neural Networks in Recommender Systems: A Survey2022