# Fast Leave-One-Out Approximation from Fragment-Target Prevalence Vectors (molFTP) : From Dummy Masking to Key-LOO for Leakage-Free Feature Construction

arXiv: https://arxiv.org/abs/2510.06029 · HTML: https://mlsanity.com/paper/2510.06029/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 7 Oct 2025.

## Builds on (most cited first, 13 of 13)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [Why Language Models Hallucinate](https://mlsanity.com/paper/2509.04664/) (2025)
- [On the Scalability of GNNs for Molecular Graphs](https://mlsanity.com/paper/2404.11568/) (2024)
- [Beyond Random Missingness: Clinically Rethinking for Healthcare Time Series Imputation](https://mlsanity.com/paper/2405.17508/) (2024)
- [Is Training Data Quality or Quantity More Impactful to Small Language Model Performance?](https://mlsanity.com/paper/2411.15821/) (2024)
- [Approximate Leave-one-out Cross Validation for Regression with ℓ1 Regularizers (extended version)](https://mlsanity.com/paper/2310.17629/) (2023)
- [Sort & Slice: A Simple and Superior Alternative to Hash-Based Folding for Extended-Connectivity Fingerprints](https://mlsanity.com/paper/2403.17954/) (2024)
- [Binary classification with ambiguous training data](https://mlsanity.com/paper/2011.02598/) (2020)
- [Improving classifier decision boundaries using nearest neighbors](https://mlsanity.com/paper/2310.03927/) (2023)
- [Simultaneous analysis of approximate leave-one-out cross-validation and mean-field inference](https://mlsanity.com/paper/2501.02624/) (2025)
- [Z-Error Loss for Training Neural Networks](https://mlsanity.com/paper/2506.02154/) (2025)
- [Bond-Centered Molecular Fingerprint Derivatives: A BBBP Dataset Study](https://mlsanity.com/paper/2510.04837/) (2025)

## Abstract (arXiv)

We introduce molFTP (molecular fragment-target prevalence), a compact representation that delivers strong predictive performance. To prevent feature leakage across cross-validation folds, we implement a dummy-masking procedure that removes information about fragments present in the held-out molecules. We further show that key leave-one-out (key-loo) closely approximates true molecule-level leave-one-out (LOO), with deviation below 8% on our datasets. This enables near full data training while preserving unbiased cross-validation estimates of model performance. Overall, molFTP provides a fast, leakage-resistant fragment-target prevalence vectorization with practical safeguards (dummy masking or key-LOO) that approximate LOO at a fraction of its cost.