Anchor Data Augmentation as a Generalized Variant of C-Mixup
by AnchoringNovember 14th, 2024
Too Long; Didn't Read
ADA generalizes C-Mixup by mixing multiple samples based on their cluster membership, preserving nonlinear relationships in augmented regression data. The approach allows augmentations to stay within or extend beyond the convex hull of original samples, improving data diversity while maintaining model accuracy.
Authors:
(1) Nora Schneider, Computer Science Department, ETH Zurich, Zurich, Switzerland ([email protected]);
(2) Shirin Goshtasbpour, Computer Science Department, ETH Zurich, Zurich, Switzerland and Swiss Data Science Center, Zurich, Switzerland ([email protected]);
(3) Fernando Perez-Cruz, Computer Science Department, ETH Zurich, Zurich, Switzerland and Swiss Data Science Center, Zurich, Switzerland ([email protected]).
Table of Links
2 Background
3.1 Comparison to C-Mixup and 3.2 Preserving nonlinear data structure
4 Experiments and 4.1 Linear synthetic data
4.2 Housing nonlinear regression
4.3 In-distribution Generalization
4.4 Out-of-distribution Robustness
5 Conclusion, Broader Impact, and References
A Additional information for Anchor Data Augmentation
3.1 Comparison to C-Mixup
3.2 Preserving nonlinear data structure
The AR modification Equations 5 and 6 do not preserve the nonlinear relation between the target and predictors,
This paper is available on arxiv under CC0 1.0 DEED license.
L O A D I N G
. . . comments & more!
. . . comments & more!
