TigerGraph, a company that provides a graph database and analytics software, has expanded its data science library with 20 new algorithms, bringing its total to more than 50 algorithms.

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 ...

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