Factorized Graph Representations for Semi-Supervised Learning from Sparse Data

1 code implementation • 5 Mar 2020 • Krishna Kumar P., Paul Langton, Wolfgang Gatterbauer

We answer this question affirmatively and suggest a method called distant compatibility estimation that works even on extremely sparsely labeled graphs (e. g., 1 in 10, 000 nodes is labeled) in a fraction of the time it later takes to label the remaining nodes.

General Classification Management +1