Closed boraturant closed 4 years ago
Also interested in this topic.
Hey Bora & Lita,
Thank you for your interests in NSL : )
First, NSL is a TF library and also part of TF ecosystem, which means users can enjoy all the nice features (eager execution, Keras APIs, distributed training, etc) from TF2.0 when using NSL. NSL also provides graph tools for users to construct & parse the graphs.
In terms of graph algorithms, NSL currently focuses on graph regularization and related techniques. From my personal understanding, GraphSage focuses more on learning node embeddings by using random walk, and Graphnet provides fundamental operations for users to build custom graph models.
We do have an ambition to include more graph algorithms & models in the NSL framework : ) You are welcome to suggest graph algorithms that you want to play with when using the NSL framework.
Hi,
Any comment on how NSL positioned with respect to DeepMind's Graphnet, or Graphsage?