5 new algorithms + streamlined onboarding are the features of StellarGraph 0.11, with substantial API, documentation + demo improvements. Full release notes: https://github.com/stellargraph/stellargraph/releases/tag/v0.11.0

New algorithms * Watch Your Step: computes node embeddings by simulating the effect of random walks, rather than doing them * Deep Graph Infomax: performs unsupervised node representation learning * Temporal Random Walks (Continuous-Time Dynamic Network Embeddings): random walks that respect the time that each edge occurred * ComplEx: computes multiplicative complex-number embeddings for entities + relationships (edge types) in knowledge graphs, used for link prediction * DistMult: computes multiplicative real-number embeddings for entities + relationships (edge types) in knowledge graphs, used for link prediction

A 6th algorithm is in development, available as an experimental preview * GCNSupervisedGraphClassification: supervised graph classification model based on Graph Convolutional layers (GCN).

Enhancements + bug fixes * StellarGraph.to_adjacency_matrix is at least 15x faster on undirected graphs * ClusterNodeGenerator is faster, reducing time to train + predict with a ClusterGCN model * Added subgraph method for computing a node-induced subgraph * Added connected_components method for computing the nodes involved in each connected component in a StellarGraph * Info method improved for heterogeneous graphs with many types + also shows info about the size + type of each node type's feature vectors * 4 new datasets in stellargraph.datasets * Neo4j functionality now tested on CI * Example Jupyter notebooks can now run directly in Google Colab + Binder * New notebooks demonstrating how to construct a StellarGraph object from Pandas + NetworkX.

Find StellarGraph on GitHub: https://github.com/stellargraph/stellargraph