TigerGraph The TigerGraph Analytics Platform combines a graph storage engine, a graph processing engine, and three types of API. It can run on-premises, in the cloud, or in a hybrid configuration.

“In our DGL (deep graph library), for example, there’s an extension of (Meta’s) Pytorch geometric that supports graph neural networks,” he said.

Deep learning faces challenges in complex language and scene understanding, reasoning about structured data, transferring learning beyond the training conditions, and learning from small amounts of ...