PyTorch-BigGraph

I spent some time experimenting with https://github.com/facebookresearch/PyTorch-BigGraph and a few other libraries, I ran into some challenges given that my dataset was very large (O(100M) edges) and very sparse; and didn't pursue it further. The papers you linked are very interesting, I will have to dig further! One more recent writeup: https://eng.uber.com/uber-eats-graph-learning/ -- a real production use case, seems promising to explore more.

1) What do you think about hybrid approach: hypergraphs + large-scale NLP models (transformers)? 2) How far we're from real self-evolving cognitive architectures with self-awareness features? Is it a question of years, months, or it's already solved problem? 3) Does it make sense to use embeddings like https://github.com/facebookresearch/PyTorch-BigGraph to achieve better results? 4) Why Cycorp decided to limit communication and collaboration with scientific community / AI-enthusiasts at some point? 5) Did you try to solve GLUE / SUPERGLUE / SQUAD challenges with your system? 6) Is Douglas Lenat still contribute actively to the project? Thanks