{
  "abstract": "The limited transferability of machine-learned interatomic potentials (MLIPs) to unseen chemical compositions constrains their utility in computational materials discovery. We present a systematic investigation into two interdependent design principleslearned atomic representations and cross-element parameterizationthat govern MLIP generalization. Using the diverse, multielement OC20 catalyst dataset, we evaluate chemically informed atomic embeddings against conventional 1-hot encoding within two distinct model architectures: the tensor-based LATTE descriptor and the MACE message-passing neural network. We demonstrate that embeddings such as Magpie and Matscholar reduce force mean absolute errors (MAEs) by 20–30% compared to 1-hot encoding, and improve data efficiency in low-data regimes by over 40%. Furthermore, by strategically sharing parameters across elements, we reduce the model sizes by up to 98% (from 23M to 400k parameters) without remarkably compromising accuracy, and even enable meaningful few-shot prediction for underrepresented elements. This work establishes a practical framework for building compact, transferable, and data-efficient MLIPs suitable for exploration across heterogeneous chemical spaces.",
  "abstract_shown": true,
  "affiliations": [
    "Scuola Internazionale Superiore di Studi Avanzati (SISSA), 34136 Trieste, Italy"
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 3,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Mina Taleblou",
      "orcid": "0000-0003-2434-461X"
    },
    {
      "affs": [
        0
      ],
      "name": "Franco Pellegrini"
    },
    {
      "affs": [
        0
      ],
      "name": "Stefano de Gironcoli",
      "orcid": "0000-0002-2307-0998"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/cr3x1am6fdh69.bib",
  "cited_by": 0,
  "doi": "10.1021/acs.jcim.6c01725",
  "fulltext_url": "https://pmc.ncbi.nlm.nih.gov/articles/PMC13715492/",
  "id": "cr3x1am6fdh69",
  "issns": [
    "1549-9596",
    "1549-960X"
  ],
  "landing_url": "https://doi.org/10.1021/acs.jcim.6c01725",
  "language": "en",
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "heading",
      "Article"
    ],
    [
      "heading",
      "Machine Learning and Deep Learning"
    ],
    [
      "openalex",
      "2505|Machine Learning in Materials Science"
    ]
  ],
  "openalex": "W7216290642",
  "pdf_url": "https://pubs.acs.org/jcisd8/article-pdf/doi/10.1021/acs.jcim.6c01725/68738484/acs.jcim.6c01725.pdf",
  "pmcid": "PMC13715492",
  "pmid": "42929556",
  "published": "2026-10-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/cr3x1am6fdh69.ris",
  "sources": [
    {
      "first_seen": "2026-11-01T12:22:47Z",
      "native_id": "PMC13715492",
      "source": "pmc",
      "url": "https://doi.org/10.1021/acs.jcim.6c01725"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "openalex:2505|Machine Learning in Materials Science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Enhanced Generalization through Atomic Embeddings and Cross-Element Parameterization",
  "title_text": "Enhanced Generalization through Atomic Embeddings and Cross-Element Parameterization",
  "type": "peer-reviewed",
  "updated_at": "2026-11-01T12:22:47Z",
  "url": "https://research.draconitic.com/paper/cr3x1am6fdh69",
  "venue": "Journal of Chemical Information and Modeling",
  "versions": []
}