Ensemble Mask Networks

Can an ${\mathbb{R}}^n\to {\mathbb{R}}^n$ 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 $\phi (A,x)\to Ax$, motivating the mechanisms introduced with applications towards litmus-testing dependencies or interaction order in graph-based models.