Skip to main content
[Preprint]. 2023 Aug 28:2023.08.26.554851. [Version 1] doi: 10.1101/2023.08.26.554851

Table 1 |.

Predictive performance.

Model R2
concatenation 0.6066 ± 0.0165
shift 0.7060 ± 0.0304
scale 0.7113 ± 0.0081
FiLM 0.7089 ± 0.0040
structural ablation 0.3016 ± 0.0304

Average performance and standard error of 5 models trained across identical data folds.