GIF by zolloc

Artificial Intelligence & the Shape of Large Data

Google AI is increasingly. understanding the differences and similarities between complex large datasets

With vast datasets understanding the shape might be important. If you could understand the similarities, alignment or discontinuity of a large set of data would it be useful? A recent article at the Google AI blog named Understanding the Shape of Large-Scale Data approaches this problem.

Graphs are discrete objects that can model the relationships between many different types of data, including web pages (left), social connections (center), or molecules (right). from article by Google AI.
  1. Then predict some property of each one as an aggregate (i.e., one label per graph).
  • DDGK introduces a mechanism for automatically learning alignments between datasets.
Left: The well-known Karate graph represents the social interactions of two martial arts clubs. Right: The spectral descriptors (NetLSD, VNGE, and Estrada Index) computed for the original graph in blue and the version with removed edges in red. Photo by: Google AI.

AI Policy and Ethics at Student at University of Copenhagen MSc in Social Data Science. All views are my own.