Pith. sign in

The entries of W are drawn from one of four distributions: U(0,1) , N(0,1) , Beta(1,1) , or Bernoulli(0.5)

These transformations include normalization (standard or min-max scaling), followed by a linear transformation in which the dataset is multiplied by a randomly sampled matrix W∈R d×d · 2023

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

citation-role summary

method 1

citation-polarity summary

use method 1

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

method 1

polarities

use method 1

representative citing papers

Feature Shift Localization Network

cs.LG · 2025-06-10 · conditional · novelty 6.0

FSL-Net localizes shifted features between two datasets using a network trained on 1,350 datasets, matching DataFix's F1 while being about 36x faster on average.

citing papers explorer

Showing 1 of 1 citing paper.

  • Feature Shift Localization Network cs.LG · 2025-06-10 · conditional · none · ref 5

    FSL-Net localizes shifted features between two datasets using a network trained on 1,350 datasets, matching DataFix's F1 while being about 36x faster on average.