From: The role of classifiers and data complexity in learned Bloom filters: insights and recommendations
SVM | DT | RF-10 | RF-20 | NN-25 | NN-150,50 | NN-200,75 |
---|---|---|---|---|---|---|
Synthetic Data | ||||||
\(1.278\cdot 10^{-8}\) | \(2.651\cdot 10^{-8}\) | \(4.425\cdot 10^{-7}\) | \(8.968\cdot 10^{-7}\) | \(8.494\cdot 10^{-6}\) | \(9.257\cdot 10^{-6}\) | \(1.008\cdot 10^{-5}\) |
SVM | DT | RF-10 | RF-20 | NN-7 | NN-150,35 | NN-175,70 |
---|---|---|---|---|---|---|
URL Data | ||||||
\(3.730\cdot 10^{-8}\) | \(6.515\cdot 10^{-8}\) | \(5.815\cdot 10^{-7}\) | \(9.930\cdot 10^{-7}\) | \(6.825\cdot 10^{-6}\) | \(7.018\cdot 10^{-6}\) | \(7.198\cdot 10^{-6}\) |
SVM | DT | RF-10 | RF-100 | NN-7 | NN-125,50 | NN-500,150 |
---|---|---|---|---|---|---|
DNA Data | ||||||
\(2.87\cdot 10^{-8}\) | \(1.236\cdot 10^{-7}\) | \(5.572\cdot 10^{-7}\) | \(5.364\cdot 10^{-6}\) | \(6.572\cdot 10^{-6}\) | \(8.138\cdot 10^{-6}\) | \(1.044\cdot 10^{-5}\) |