Graph embedding refers to learning low-dimensional representations of nodes in a network; the representation encodes structural information and node features. Such a representation can then be used for various downstream machine learning tasks like node classification, link prediction, visualization, etc. The downstream tasks often work with dynamic or evolving networks such as social networks, recommendation networks etc. The majority of the graph embedding methods assume fixed graph structure and thus are unsuitable for dynamic networks. The GraphSAGE embedding method overcomes this limitation by incorporating two changes, sampling and aggregating features, in the graph convolutional networks (GCNs) that are used for fixed structure networks. These changes, explained below, make GraphSAGE not only computationally efficient to scale to very large graphs but also permit embeddings to be generated for those nodes of a graph not seen before. This inductive capability to work with unsee

# Eclectic-AI

A blog about assorted topics from machine learning including deep learning, natural language processing and graph-based methods.