Delta-learned force fields for nonbonded interactions: Addressing the strength mismatch between covalent-nonbonded interaction for global models

• URL: http://arxiv.org/abs/2511.01913v1
• Date: Sat, 01 Nov 2025 06:15:05 GMT
• Title: Delta-learned force fields for nonbonded interactions: Addressing the strength mismatch between covalent-nonbonded interaction for global models
• Abstract summary: We introduce textit$Delta$-sGDML, a scale-aware formulation that decouples intra- and intermolecular physics by training fragment-specific models and composing them at inference.<n>We show that textit$Delta$-sGDML delivers consistent gains over a single global model, with fragment-resolved force-error reductions up to textbf75%, without loss of energy accuracy.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Noncovalent interactions--vdW dispersion, hydrogen/halogen bonding, ion-$\pi$, and $\pi$-stacking--govern structure, dynamics, and emergent phenomena in materials and molecular systems, yet accurately learning them alongside covalent forces remains a core challenge for machine-learned force fields (MLFFs). This challenge is acute for global models that use Coulomb-matrix (CM) descriptors compared under Euclidean/Frobenius metrics in multifragment settings. We show that the mismatch between predominantly covalent force labels and the CM's overrepresentation of intermolecular features biases single-model training and degrades force-field fidelity. To address this, we introduce \textit{$\Delta$-sGDML}, a scale-aware formulation within the sGDML framework that explicitly decouples intra- and intermolecular physics by training fragment-specific models alongside a dedicated binding model, then composing them at inference. Across benzene dimers, host-guest complexes (C$_{60}$@buckycatcher, NO$_3^-$@i-corona[6]arene), benzene-water, and benzene-Na$^+$, \mbox{$\Delta$-sGDML} delivers consistent gains over a single global model, with fragment-resolved force-error reductions up to \textbf{75\%}, without loss of energy accuracy. Furthermore, molecular-dynamics simulations further confirm that the $\Delta$-model yields a reliable force field for C$_{60}$@buckycatcher, producing stable trajectories across a wide range of temperatures (10-400~K), unlike the single global model, which loses stability above $\sim$200~K. The method offers a practical route to homogenize per-fragment errors and recover reliable noncovalent physics in global MLFFs.

Related papers

• Unsupervised Thermodynamics of Molecular Diffusion Models: Action-Operator Semantics and Auditable Free-Energy Readout [0.0]
  We introduce a mathematically consistent action-operator framework compatible with diffusion models.<n>We show that incorporating physical inductive biases enables partial recovery of the base action and perturbation operator.
  arXiv  Detail & Related papers  (2026-06-28T14:45:31Z)
• Fault-tolerant simulation of the electronic structure using Projector Augmented-Waves and Bloch orbitals [43.936586633107396]
  We present the Bloch--UPAW framework that combines Bloch-orbital $k$-space structure with unitary projector-augmented-wave augmentation.<n>We derive a linear-combination-of-unitaries decomposition and a block-encoding circuit suitable for qubitization.<n>Asymptotically, the Toffoli cost scales as $mathcalO(N_k3)$ when refining the $k$-mesh and as $mathcalO(N_a3.5)$ when enlarging the supercell.
  arXiv  Detail & Related papers  (2026-04-13T23:46:58Z)
• Dispersion Loss Counteracts Embedding Condensation and Improves Generalization in Small Language Models [55.908141398092646]
  Large language models (LLMs) achieve remarkable performance through ever-increasing parameter counts, but scaling incurs steep computational costs.<n>We study representational differences between LLMs and their smaller counterparts, with the goal of replicating the representational qualities of larger models in the smaller models.<n>We show that small models such as $textttGPT2$ and $textttQwen3-0.6B$ exhibit severe condensation, whereas the larger models such as $textttGPT2-xl$ and $textttQwen3-32B
  arXiv  Detail & Related papers  (2026-01-30T16:07:03Z)
• Scalable Machine Learning Force Fields for Macromolecular Systems Through Long-Range Aware Message Passing [18.50744268453995]
  Machine learning force fields (MLFFs) have revolutionized molecular simulations by providing quantum mechanical accuracy at the speed of molecular mechanical computations.<n>However, a fundamental reliance of these models on fixed-cutoff architectures limits their applicability to macromolecular systems where long-range interactions dominate.<n>We demonstrate that this locality constraint causes force prediction errors to scale monotonically with system size, revealing a critical architectural bottleneck.<n>We introduce E2Former-LSR, an equivariant transformer that explicitly integrates long-range attention blocks. E2Former-LSR achieves stable error scaling, superior fidelity in capturing non-covalent decay, and
  arXiv  Detail & Related papers  (2026-01-07T10:12:34Z)
• Torsional-GFN: a conditional conformation generator for small molecules [75.91029322687771]
  We introduce a conditional GFlowNet specifically designed to sample conformations of molecules proportionally to their Boltzmann distribution.<n>Our work presents a promising avenue for scaling the proposed approach to larger molecular systems.
  arXiv  Detail & Related papers  (2025-07-15T21:53:25Z)
• Energy-Based Coarse-Graining in Molecular Dynamics: A Flow-Based Framework without Data [0.0]
  Coarse-grained (CG) models provide an effective route to reducing the complexity of molecular simulations.<n>We introduce a fully data-free, generative framework for CG that directly targets the all-atom Boltzmann distribution.<n>We show that the method captures all relevant modes of the Boltzmann distribution, reconstructs atomic configurations, and automatically learns physically meaningful CG representations.
  arXiv  Detail & Related papers  (2025-04-29T17:05:27Z)
• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling [90.23688195918432]
  3D molecule generation is crucial for drug discovery and material science.<n>Existing approaches typically maintain separate latent spaces for invariant and equivariant modalities.<n>We propose textbfUAE-3D, a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space.
  arXiv  Detail & Related papers  (2025-03-19T08:56:13Z)
• Boltzmann-Aligned Inverse Folding Model as a Predictor of Mutational Effects on Protein-Protein Interactions [48.58317905849438]
  Predicting the change in binding free energy ($Delta Delta G$) is crucial for understanding and modulating protein-protein interactions. We propose the Boltzmann Alignment technique to transfer knowledge from pre-trained inverse folding models to $Delta Delta G$ prediction.
  arXiv  Detail & Related papers  (2024-10-12T14:13:42Z)
• Collective dynamics Using Truncated Equations (CUT-E): simulating the collective strong coupling regime with few-molecule models [0.0]
  We exploit permutational symmetries to drastically reduce the computational cost of textitab-initio quantum dynamics simulations for large $N$. We show that addition of $k$ extra effective molecules is enough to account for phenomena whose rates scale as $mathcalO(N-k)$.
  arXiv  Detail & Related papers  (2022-09-11T22:49:29Z)
• Moser Flow: Divergence-based Generative Modeling on Manifolds [49.04974733536027]
  Moser Flow (MF) is a new class of generative models within the family of continuous normalizing flows (CNF) MF does not require invoking or backpropagating through an ODE solver during training. We demonstrate for the first time the use of flow models for sampling from general curved surfaces.
  arXiv  Detail & Related papers  (2021-08-18T09:00:24Z)
• BIGDML: Towards Exact Machine Learning Force Fields for Materials [55.944221055171276]
  Machine-learning force fields (MLFF) should be accurate, computationally and data efficient, and applicable to molecules, materials, and interfaces thereof. Here, we introduce the Bravais-Inspired Gradient-Domain Machine Learning approach and demonstrate its ability to construct reliable force fields using a training set with just 10-200 atoms.
  arXiv  Detail & Related papers  (2021-06-08T10:14:57Z)
• Boundary time crystals in collective $d$-level systems [64.76138964691705]
  Boundary time crystals are non-equilibrium phases of matter occurring in quantum systems in contact to an environment. We study BTC's in collective $d$-level systems, focusing in the cases with $d=2$, $3$ and $4$.
  arXiv  Detail & Related papers  (2021-02-05T19:00:45Z)
• Extended Falicov-Kimball model: Hartree-Fock vs DMFT approach [0.0]
  We study the extended Falicov-Kimball model at half-filling within the Hartree-Fock approach (HFA) We show that the HFA description of the ground state properties of the model is equivalent to the exact DMFT solution.
  arXiv  Detail & Related papers  (2020-11-15T10:43:55Z)
• Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles [3.0980025155565376]
  "MuML" models are fitted together to reproduce molecular $boldsymbolmu$ computed using high-level coupled-cluster theory. We demonstrate that the uncertainty in the predictions can be estimated reliably using a calibrated committee model.
  arXiv  Detail & Related papers  (2020-03-27T14:35:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.