The down votes from non-subscribed accounts are amusing to me. These people clearly are looking for their “all” feed to be curated in some way. Ironically, machine learning could potentially help with that, but there are many people burnt out by the hype cycle (I don’t blame them).

Regarding the article. It looks like the advancement here is finding methods to efficiently use sets of graphs which are an order of magnitude larger than prior methods could use for training? They also seem to have used more sets of graphs than prior models across a wider set of domains. Am I reading this correctly?