Neural Network-Based Approach
Explore neural network-based approaches to generate graph embeddings, including methods like Structural Deep Network Embedding and Large-scale Information Network Embedding. Understand how these algorithms preserve node proximities using autoencoders and edge sampling, and learn dimensionality reduction techniques such as t-SNE and PCA to analyze embeddings effectively.
We'll cover the following...
Deep autoencoders
Neural network methods like deep autoencoders generate graph embeddings using an encoder-decoder model. A few of the embedding algorithms that use neural networks are listed below.
Structural deep network embedding (SDNE)
This algorithm tries to preserve the first- and second-order proximities. The first-order proximity defines the pairwise proximity of the nodes—that is, a first-order proximity exists between node u and node v if a link exists between them. The second-order proximity between two nodes means there is neighborhood network ...