Multi-Scale attributed node embedding

We present network embedding algorithms that capture information about a node from the local distribution over node attributes around it, as observed over random walks following an approach similar to Skip-gram. Observations from neighbourhoods of different sizes are either pooled (AE) or encoded distinctly in a multi-scale approach (MUSAE). Capturing attribute-neighbourhood relationships over multiple scales is useful for a range of applications, including latent feature identification across disconnected networks with similar features. We prove theoretically that matrices of node-feature pointwise mutual information are implicitly factorized by the embeddings. Experiments show that our algorithms are computationally efficient and outperform comparable models on social networks and web graphs.

Automated summary

Our network embedding algorithms capture information from the local distribution over node attributes, either by pooling observations from different-sized neighborhoods or encoding them distinctly in a multi-scale approach. The algorithms are computationally efficient and outperform comparable models on social networks and web graphs. This approach is useful for a range of applications, including identifying latent features across disconnected networks with similar attributes.