In most tutorials I have seen, training happens over a single large knowledge graph. Is there a way to generalise based on multiple small knowledge graphs of the same node and edge type, but different feature vector ofcourse in each graph. Any inputs, including resources are appreciated.
Thank you for your time!
You could treat those knowledge graphs as a bigger graph with different connected components. Then you could train on this bigger graph as usual.
Could you kindly refer me to some good resources I could read up on the same? I didn’t quite understand the answer. Thank you for your time. Much appreciated
This topic was automatically closed 30 days after the last reply. New replies are no longer allowed.