KGATE: A modular autoencoder for graph representation learning applied to target gene identification in aging diseases.

Knowledge Graph Embedding (KGE) is a graph representation learning technique that learns a vectorial representation of knowledge graph nodes and edges. The most common architecture for KGE models is the autoencoder: an encoder transforms the knowledge graph into a vectorial representation and a decoder attempts to reconstruct the original graph from the latent space. However, current KGE libraries are limited as they do not fully adopt the autoencoder architecture and lack interoperability.

KGATE (Knowledge Graph Autoencoder Training Environment) is designed to address the limitations of current KGE libraries. KGATE assembles each part of an autoencoder as fine-tunable modular blocks. As a general-purpose KGE library, KGATE can easily benchmark and fast prototype many encoder-decoder combinations in a reproducible manner. In addition, KGATE implements the building blocks for temporal embeddings of knowledge graphs, and handles the most common graph temporal representations.