Deep Graph LibraryFramework Agnostic Build your models with PyTorch, TensorFlow or Apache MXNet. Efficient and Scalable Fast and memory-efficient message passing primitives for training Graph Neural Networks. Scale to giant graphs via multi-GPU acceleration and distributed training infrastructure. Diverse Ecosystem DGL empowers a variety of domain-specific projects including DGL-KE for learning large-scale knowledg
GluonTS: Probabilistic Time Series Models in Python
http://www.vldb.org/pvldb/vol11/p2102-faloutsos.pdf
