提出新方法防止生化数据中的关系泄露，提升模型评估真实性
Refnd: Preventing Data Leakage in Relational Datasets
- 基于关系生成过程建模数据结构，用近邻图加速分割
- 在抗菌肽数据集上表现更真实，避免传统方法的性能虚高
- 适用于蛋白、小分子等多类生物数据，开源可用
基于生化数据训练的机器学习模型常采用未考虑关系结构的划分方式，导致信息泄露和性能估计过高。现有分割方法缺乏理论基础，且计算复杂度最高为二次方。本文提出关系生成过程（RGP）的数学形式化，解释生化数据中关系结构的成因，并设计了Refnd分割算法，利用分层可导航小世界（HNSW）在近线性时间内构建邻近图。在抗菌肽数据集上的验证表明，Refnd分割得到的评估性能更低但更真实。该方法适用于所有符合RGP的数据，如蛋白质序列与结构、小分子、核酸序列，已开源为支持Rust加速的Python包：pip install refnd。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。