arXiv (Cornell University) · 2019 · 39 citations · 14 references
ComputingData ScienceEdge ComputingFeature EngineeringMachine LearningDirected Acyclic GraphsGraph AlgorithmsGraph AnalyticsGraph MiningGraph TheoryGraph-based LearningConvolutional Neural NetworksDirected GraphsGraph ClassificationGraph Convolutional NetworksGraph Feature ExtractionGraph Neural NetworksSemi-supervised ClassificationSemi-supervised Learning On Graphs
Graph convolutional networks(GCNs) have become the most popular approaches for graph data in these days because of their powerful ability to extract features from graph. GCNs approaches are divided into two categories, spectral-based and spatial-based. As the earliest convolutional networks for graph data, spectral-based GCNs have achieved impressive results in many graph related analytics tasks. However, spectral-based models cannot directly work on directed graphs. In this paper, we propose an improved spectral-based GCN for the directed graph by leveraging redefined Laplacians to improve its propagation model. Our approach can work directly on directed graph data in semi-supervised nodes classification tasks. Experiments on a number of directed graph datasets demonstrate that our approach outperforms the state-of-the-art methods.
14
Deep Learning On Graphs (Graphsip Summer School)
Michaël Defferrard · Figshare · 2016 · 5.1K citations
{SNAP Datasets}: {Stanford} Large Network Dataset Collection
Jure Leskovec, Andrej Krevl · 2014 · 2.8K citations
Deep Convolutional Networks on Graph-Structured Data
Mikael Henaff, Joan Bruna, Yann LeCun · arXiv (Cornell University) · 2015 · 1.4K citations · Full text