{
  "abstract": "In molecular property prediction, labeled data are often limited to tens to thousands of samples, yet it remains unclear which model classes are most effective in these low-data regimes and how their ranking evolves with data size. We present a learning-curve benchmark spanning traditional machine learning, graph neural networks, transformer-based molecular language models, rotationally equivariant and SE(3)-invariant 3D networks, descriptor-based hybrids, multi-task learning variants, and graph–sequence fusion baselines. Training size is varied from 50 to 3,000 samples, with dataset-dependent maxima, on QM9, ESOL, Lipophilicity, and BACE under scaffold splits with repeated trials. Four patterns emerge. (1) Model optimality is regime-dependent: deep learning leads continuous physicochemical properties (ESOL, Lipophilicity) while Gaussian Process Regression leads bioactivity (BACE) across most of the range, with clear traditional-versus-deep-learning crossovers. (2) The benefit of 3D inductive bias is target-dependent: on QM9 an equivariant 3D network trained on DFT geometries is strong on LUMO and the HOMO–LUMO gap but weak on HOMO, although all three targets use the same DFT-optimized geometries; single-conformer ETKDG inputs instead give near-flat curves on Lipophilicity and BACE. (3) Pretraining chiefly raises the low-data floor rather than the mean. Its advantage concentrates where no single model dominates, typically at intermediate sizes, and its clearest effect is on worst-case accuracy: in a matched Uni-Mol pair, pretraining lifts the minimum QM9 R² at N≤200 by approximately 0.6 on every target. Neither parameter count nor pretraining-corpus size predicts the ranking — the compact ChemBERTa-2 (3.4M parameters) outperforms the far larger MoLFormer (44.5M) and SELFormer (86.8M) on ESOL, yet the ordering reverses on the other datasets. (4) Under data scarcity, model selection beats averaging: even oracle ensembles barely improve on the best single model at the smallest sizes (at most +1.2% in RMSE at N=50, and negative on ESOL). Together these results give data-scale-aware guidelines for model selection and establish learning-curve analysis as a principled tool for characterizing model behavior across the property–scale plane. Scientific Contribution: This study establishes a comprehensive learning-curve benchmark for molecular property prediction in low-data regimes, comparing a broad suite of model families across four datasets spanning physicochemical, quantum-mechanical, and bioactivity properties. It shows that the best-performing model family is jointly determined by data scale and target type — including reproducible crossovers between traditional machine learning and deep learning — and converts these findings into actionable, data-scale-aware model-selection guidelines.",
  "abstract_shown": true,
  "affiliations": [
    "¹Department of Information Display",
    "Kyung Hee University"
  ],
  "article_type": null,
  "arxiv": null,
  "author_total": 1,
  "authors": [
    {
      "affs": [
        0,
        1
      ],
      "name": "Junho Lee¹",
      "orcid": "0009-0008-1540-7694"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/a2dfrvtse1fhf.bib",
  "cited_by": 0,
  "doi": "10.26434/chemrxiv.15001253/v6",
  "fulltext_url": null,
  "id": "a2dfrvtse1fhf",
  "issns": [],
  "landing_url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15001253/v6",
  "language": null,
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1703|Computational Drug Discovery Methods"
    ]
  ],
  "openalex": "W7204912416",
  "pdf_url": "https://chemrxiv.org/doi/pdf/10.26434/chemrxiv.15001253/v6",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-01",
  "publisher": "American Chemical Society (ACS)",
  "ris": "https://research.draconitic.com/paper/a2dfrvtse1fhf.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:17:17Z",
      "native_id": "10.26434/chemrxiv.15001253",
      "source": "chemrxiv",
      "url": "https://chemrxiv.org/doi/full/10.26434/chemrxiv.15001253/v6"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "source:chemrxiv",
      "subfield": "general"
    }
  ],
  "title": "When Do Models Win? A Learning Curve Benchmark for Molecular Property Prediction in Low-Data Regimes",
  "title_text": "When Do Models Win? A Learning Curve Benchmark for Molecular Property Prediction in Low-Data Regimes",
  "type": "preprint",
  "updated_at": "2026-10-30T12:17:17Z",
  "url": "https://research.draconitic.com/paper/a2dfrvtse1fhf",
  "venue": "ChemRxiv",
  "versions": []
}