The method name itself contains suffix SAGE (SAmple and aggreGatE) but you didn't mention anything about the sampling part - and that's arguably one of the most important parts of this work - which made this method applicable to huge graphs.

I'd just suggest you consider updating the blog with that information. Thanks!

I just read the paper and was looking for some details around sampling as that part confused me a bit - that's why I'm commenting. Stay safe!