Further reading

If you want to learn more about graph embeddings, I recommend the following readings:

• Graph Machine Learning by C. Stamile, A. Marzullo,and E. Deusebio, Packt Publishing. It’s a comprehensive introduction to Graph ML. Both supervised and unsupervised algorithms are covered, with applications in various fields including natural language processing (NLP), using networkx and Python ML libraries such as tensorflow. It is a nice complement to this book. As an exercise, you can try to redo the analyses presented in the GML book using the tools we are discussing in this book, Neo4j and GDS.
• P-GNN algorithm—I talked about this in the Positional or structural section: https://snap.stanford.edu/pgnn/
• I presented some graph embedding algorithms in this Medium story: https://medium.com/@st3llasia/graph-embedding-techniques-7d5386c88c5
• The original DeepWalk paper: https://arxiv.org/abs/1403.6652
• The original Node2Vec paper: https://arxiv.org...