Skip to content
Branch: master
Find file History
Pull request Compare This branch is 1 commit ahead, 35 commits behind develop.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
ensembles Removed flatten_output parameter in node_model for GraphSAGE. Sep 9, 2019
use-cases Reverted twitter demo Oct 28, 2019

Table of Contents

This folder contains several examples of applying graph machine learning (ML) algorithms on network-structured data to solve several common problems including node attribute inference (inferring entity properties) and link prediction (predicting relations and/or their properties). The examples demonstrate using the StellarGraph library to build machine learning workflows on both homogeneous and heterogeneous networks.

Each folder contains one or more examples of using the StellarGraph implementations of the state-of-the-art algorithms, attri2vec [4], GraphSAGE [3], HinSAGE, GCN [6], GAT [7], PPNP/APPNP [9], Node2Vec [1], and Metapath2Vec [2]. GraphSAGE, HinSAGE, and GAT are variants of Graph Convolutional Neural networks [6]. Node2Vec and Metapath2Vec are methods based on graph random walks and representation learning using the Word2Vec [5] algorithm. attri2vec[4] is also based on graph random walks, and learns node representations by performing a mapping on node attributes.

The examples folder structure is shown below.

  • /embeddings

    Examples of unsupervised node representation learning for homogeneous networks, heterogeneous networks, and homogeneous networks with node features using Node2Vec, Metapath2Vec, and Unsupervised GraphSAGE algorithm, respectively.

  • /link-prediction

    Examples of using StellarGraph algorithms for link prediction on homogeneous and heterogeneous networks.

  • /node-classification

    Examples of using StellarGraph algorithms for node classification on homogeneous and heterogenous networks.

  • /ensembles

    Examples of using ensembles of graph convolutional neural networks, e.g., GraphSAGE, GCN, HinSAGE, etc., for node classification and link prediction. Model ensembles usually yield better predictions than single models, while also providing estimates of prediction uncertainty as a bonus.

  • /calibration

    Examples of calibrating graph convolutional neural networks, e.g., GraphSAGE, for binary and multi-class classification problems.

  • /community_detection

    Examples of using unsupervised GraphSAGE embeddings in a context of community detection. Community detection is demonstrated on a terrorist network, where groups of terrorist groups are found using dbscan on top of the graphSAGE embeddings. Note that this demo requires the installation of igraph-python, see the in this directory for more details.

  • /use-cases

    Example use-cases/applications for graph neural network algorithms.


  1. Node2Vec: Scalable Feature Learning for Networks. A. Grover, J. Leskovec. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 2016. (link)

  2. Metapath2Vec: Scalable Representation Learning for Heterogeneous Networks. Yuxiao Dong, Nitesh V. Chawla, and Ananthram Swami. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 135–144, 2017 (link)

  3. Inductive Representation Learning on Large Graphs. W.L. Hamilton, R. Ying, and J. Leskovec arXiv:1706.02216 [cs.SI], 2017. (link)

  4. Attributed Network Embedding via Subspace Discovery. D. Zhang, Y. Jie, X. Zhu and C. Zhang, arXiv:1901.04095, [cs.SI], 2019. (link)

  5. Distributed representations of words and phrases and their compositionality. T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean. In Advances in Neural Information Processing Systems (NIPS), pp. 3111-3119, 2013. (link)

  6. Semi-Supervised Classification with Graph Convolutional Networks. T. Kipf, M. Welling. ICLR 2017. arXiv:1609.02907 (link)

  7. Graph Attention Networks. P. Velickovic et al. ICLR 2018 (link)

  8. On Calibration of Modern Neural Networks. C. Guo, G. Pleiss, Y. Sun, and K. Q. Weinberger. ICML 2017. (link)

  9. Predict then propagate: Graph neural networks meet personalized PageRank. J. Klicpera, A. Bojchevski, A., and S. Günnemann, ICLR, 2019, arXiv:1810.05997.(link)

You can’t perform that action at this time.