paper-with-me

Papers

Simple and Deep Graph Convolutional Networks

2020-07-04 · ICML 2020 1 · Ming Chen, Zhewei Wei, Zengfeng Huang, Bolin Ding, Yaliang Li

Graph convolutional networks (GCNs) are a powerful deep learning approach for graph-structured data. Recently, GCNs and subsequent variants have shown superior performance in various application areas on real-world datasets. Despite their success, most of the current GCN models are shallow, due to the {\em over-smoothing} problem. In this paper, we study the problem of designing and analyzing deep graph convolutional networks. We propose the GCNII, an extension of the vanilla GCN model with two simple yet effective techniques: {\em Initial residual} and {\em Identity mapping}. We provide theoretical and empirical evidence that the two techniques effectively relieves the problem of over-smoothing. Our experiments show that the deep GCNII model outperforms the state-of-the-art methods on various semi- and full-supervised tasks. Code is available at https://github.com/chennnM/GCNII .

📄 PDF Abstract BibTeX arXiv:2007.02133

Code (4)

chennnM/GCNII 공식 구현 pytorch
chennnM/GCNII/tree/master/PyG/ogbn-arxiv pytorch
tyxxzjpdez/GCNII-DropGroups pytorch
zhanglab-aim/cancer-net pytorch

Tasks

Graph ClassificationGraph RegressionLink PredictionNode ClassificationNode Classification on Non-Homophilic (Heterophilic) GraphsNode Property Prediction

Methods 이 논문이 사용한 방법론

Residual Connection 설명 없음
GCNII GCNII is an extension of a Graph Convolution Networks with two new techniques, initial residual and identify mapping, to tackle…
GCN A Graph Convolutional Network, or GCN, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural…

Similar Papers 제목 키워드 기반

Simple Graph Convolutional Networks

2021-06-10 · Luca Pasa, Nicolò Navarin, Wolfgang Erb, Alessandro Sperduti

Many neural networks for graphs are based on the graph convolution operator, proposed more than a decade ago. Since then, many alternative definitions have been proposed, that tend to add complexity (and non-linearity) t…

A Simple Spectral Failure Mode for Graph Convolutional Networks

2020-10-25 · Carey E. Priebe, Cencheng Shen, Ningyuan Huang, Tianyi Chen

Neural networks have achieved remarkable successes in machine learning tasks. This has recently been extended to graph learning using neural networks. However, there is limited theoretical work in understanding how and w…

Graph EmbeddingGraph Learning

On Filter Size in Graph Convolutional Networks

2018-11-23 · Dinh Van Tran, Nicolò Navarin, Alessandro Sperduti

Recently, many researchers have been focusing on the definition of neural networks for graphs. The basic component for many of these approaches remains the graph convolution idea proposed almost a decade ago. In this pap…

Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks

2019-10-02 · Guillaume Salha, Romain Hennequin, Michalis Vazirgiannis

Graph autoencoders (AE) and variational autoencoders (VAE) recently emerged as powerful node embedding methods, with promising performances on challenging tasks such as link prediction and node clustering. Graph AE, VAE …

ClusteringLink PredictionNode Clustering

SPI-GCN: A Simple Permutation-Invariant Graph Convolutional Network

2019-04-08 · HAL archives-ouvertes 2019 4 · Asma Atamna, Nataliya Sokolovska, Jean-Claude Crivello

A wide range of machine learning problems involve handling graph-structured data. Existing machine learning approaches for graphs, however, often imply computing expensive graph similarity measures, preprocessing input g…

BIG-bench Machine LearningDeep LearningGeneral ClassificationGraph Classification+1