# Refnd: Preventing Data Leakage in Relational Datasets

arXiv: https://arxiv.org/abs/2607.19376 · HTML: https://mlsanity.com/paper/2607.19376/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 6 of 6)

- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphs](https://mlsanity.com/paper/1603.09320/) (2016)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [Lo-Hi: Practical ML Drug Discovery Benchmark](https://mlsanity.com/paper/2310.06399/) (2023)
- [SpanSeq: Similarity-based sequence data splitting method for improved development and assessment of deep learning projects](https://mlsanity.com/paper/2402.14482/) (2024)

## Abstract (arXiv)

Machine learning models trained on biochemical data are routinely evaluated using splits that fail to account for relational structure, causing information leakage and over-optimistic performance estimates. Existing splitting methods lack theoretical grounding and scale at best quadratically. We introduce the Relational Generative Process (RGP), a mathematical formalization explaining why relational structure arises in biochemical datasets, and Refnd, a splitting algorithm that leverages a proximity graph computed in loglinear time using Hierarchical Navigable Small World (HNSW). We validate on an antimicrobial peptide dataset, showing that Refnd splits yield lower but more realistic evaluation performance than traditional splits. Refnd is applicable to any dataset arising from an RGP such as protein sequences and structures, small molecules, and nucleotide sequences, and is openly available as a Rust accelerated Python package: pip install refnd.