Migration as a Probe: A Generalizable Benchmark Framework for Specialist vs. Generalist Machine-Learned Force Fields
This provides practical guidelines for MLFF development in computational materials science, though it is incremental as it focuses on benchmarking within an existing architecture.
The paper tackled the problem of evaluating specialist vs. generalist machine-learned force fields by introducing a benchmarking framework using defect migration pathways, finding that fine-tuned models substantially outperform from-scratch and zero-shot approaches for kinetic properties but show partial loss of long-range physics.
Machine-learned force fields (MLFFs), especially pre-trained foundation models, are transforming computational materials science by enabling ab initio-level accuracy at molecular dynamics scales. Yet their rapid rise raises a key question: should researchers train specialist models from scratch, fine-tune generalist foundation models, or use hybrid approaches? The trade-offs in data efficiency, accuracy, cost, and robustness to out-of-distribution failure remain unclear. We introduce a benchmarking framework using defect migration pathways, evaluated through nudged elastic band trajectories, as diagnostic probes that test both interpolation and extrapolation. Using Cr-doped Sb2Te3 as a representative two-dimensional material, we benchmark multiple training paradigms within the MACE architecture across equilibrium, kinetic (atomic migration), and mechanical (interlayer sliding) tasks. Fine-tuned models substantially outperform from-scratch and zero-shot approaches for kinetic properties but show partial loss of long-range physics. Representational analysis reveals distinct, non-overlapping latent encodings, indicating that different training strategies learn different aspects of system physics. This framework provides practical guidelines for MLFF development and establishes migration-based probes as efficient diagnostics linking performance to learned representations, guiding future uncertainty-aware active learning.