Variational Approach for Learning Community Structures

Figure 1

Conceptual illustration of Variational Graph Autoencoder Framework for Community Detection (VGAECD). In the encoding phase, VGAECD first convolves on the network, learning structural and nodal features in the process. These pieces of information are then mapped into a latent representation, and which are parameters to Mixture of Gaussian Model. Subsequently, we can then sample to obtain a latent representation for each node . Finally, can be reconstructed using a decoding function, . The loss is calculated and backpropagated to the latent variables.