Local2Global: A distributed approach for scaling representation learning on graphs. (arXiv:2201.04729v1 [cs.LG])

We propose a decentralised "local2global"' approach to graph representation
learning, that one can a-priori use to scale any embedding technique. Our
local2global approach proceeds by first dividing the input graph into
overlapping subgraphs (or "patches") and training local representations for
each patch independently. In a second step, we combine the local
representations into a globally consistent representation by estimating the set
of rigid motions that best align the local representations using information
from the patch overlaps, via group synchronization. A …

arxiv distributed graphs learning scaling