Ensemble Mask Networks

09/12/2023

∙

by   Jonny Luntzel, et al.

∙

0

∙

share

Can an ℝ^n→ℝ^n feedforward network learn matrix-vector multiplication? This study introduces two mechanisms - flexible masking to take matrix inputs, and a unique network pruning to respect the mask's dependency structure. Networks can approximate fixed operations such as matrix-vector multiplication ϕ(A,x) → Ax, motivating the mechanisms introduced with applications towards litmus-testing dependencies or interaction order in graph-based models.