What's the difference between searchDepth and sampleSizes in graphSage model?


List of Integer [25, 10] yes

A list of Integer values, the size of the list determines the number of layers and the values determine how many nodes will be sampled by the layers.


Integer 5 yes

Maximum depth of the RandomWalks to sample nearby nodes for the training.

In the original paper, the K is the search depth, which is more similar to the searthDepth parameter in neo4j. What about the first parameter of sampleSizes? If the '25' is also the search depth, how is it related to searchDepth?

Thanks for explanation.