{
  "annotation_id": "c55cd774-0d22-4d72-955e-dda94b5fe462",
  "date_created": "2026-02-17T05:53:07.895000Z",
  "date_modified": "2026-02-17T05:53:07.895000Z",
  "file_hash": "64301c14eb822f4a737d1565b267e2718c799a53b7ceab55b3a4032d298654a8",
  "private": false,
  "record": {
    "abstract": "Efficient discovery of new materials demands strategies to reduce the number of costly first-principles calculations required to train predictive machine learning models. We develop and validate an active learning framework that iteratively selects informative training structures for machine-learned interatomic potentials (MLIPs) from large, heterogeneous materials databases, specifically the Materials Project and OQMD. Our framework integrates compositional and property-based descriptors with a neural network ensemble model, enabling real-time uncertainty quantification via Query-by-Committee. We systematically compare four selection strategies: random sampling (baseline), uncertainty-based sampling, diversity-based sampling (k-means clustering with farthest-point refinement), and a hybrid approach balancing both objectives. Experiments across four representative material systems (elemental carbon, silicon, iron, and a titanium-oxide compound) with 5 random seeds per configuration demonstrate that diversity sampling consistently achieves competitive or superior performance, with particularly strong advantages on complex systems like titanium-oxide (10.9% improvement, p=0.008). Our results show that intelligent data selection strategies can achieve target accuracy with 5-13% fewer labeled samples compared to random baselines. The entire pipeline executes on Google Colab in under 4 hours per system using less than 8 GB of RAM, thereby democratizing MLIP development for researchers globally with limited computational resources. Our open-source code and detailed experimental configurations are available on GitHub. This multi-system evaluation establishes practical guidelines for data-efficient MLIP training and highlights promising future directions including integration with symmetry-aware neural network architectures.",
    "arxiv_id": "2601.06916",
    "authors": [
      "Mohammed Azeez Khan",
      "Aaron D\u0027Souza",
      "Vijay Choyal"
    ],
    "categories": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Active Learning Strategies for Efficient Machine-Learned Interatomic Potentials Across Diverse Material Systems",
    "url": "https://arxiv.org/abs/2601.06916",
    "version": "v2"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "2b0f4cb4-2340-43e2-a3ac-b7994211aab6",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}