QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space

• URL: http://arxiv.org/abs/2605.10458v1
• Date: Mon, 11 May 2026 12:29:10 GMT
• Title: QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space
• Abstract summary: Quantum Topological Neural Network (QT-Net) is a rotationally augmented, non-equivariant graph neural network.<n>We show that QT-Net can be used to infer properties of atoms in molecules from QM9 outside our training set.<n>We release all code and data, including a JAX implementation of QT-Net, to support the broader use of learned QTA properties as inductive biases for atomic-scale molecular machine learning.
• Score: 5.76402440170162
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Atomic properties such as partial charges or multipoles encode chemically meaningful information that can inform downstream molecular property prediction, but their evaluation as machine learning targets has been complicated by the absence of a principled out-of-distribution evaluation protocol at the atomic level. In this work, we propose a held-out evaluation protocol that clusters atomic environments by SOAP descriptors and computes metrics accounting only for cluster labels unseen during training. Following this procedure, we use 5$\times$5 cross-validation and Tukey's HSD to run a statistically rigorous comparison of E(3)-equivariant against non-equivariant, rotationally augmented models for predicting electron populations and multipoles of H, C, N, and O atoms. Building on our results, we introduce the Quantum Topological Neural Network (QT-Net), a rotationally augmented, non-equivariant graph neural network. We show that QT-Net can be used to infer properties of atoms in molecules from QM9 outside our training set, and that these inferred properties can yield improvement when used as input features for downstream molecular property prediction. To further validate the framework, molecular dipole moments computed from QT-Net's per-atom outputs recover the ground-truth values reported in QM9. We release all code and data, including a JAX implementation of QT-Net, to support the broader use of learned QTA properties as inductive biases for atomic-scale molecular machine learning.

Related papers

• Atoms as Language: VQ-Atom: Semantic Discretization for Molecular Representation Learning [0.0]
  VQ-Atom is a semantic discretization framework that converts continuous atom-level graph representations into discrete tokens corresponding to local chemical environments.<n>We show that VQ-Atom consistently improves predictive performance compared to conventional tokenization approaches.
  arXiv  Detail & Related papers  (2026-05-16T05:45:54Z)
• Adapting Quantum Machine Learning for Energy Dissociation of Bonds [6.247064060111601]
  We present a benchmark comparing quantum and classical machine learning models for bond energies prediction.<n>Top-performing quantum models (QCNN, QRF) match the predictive accuracy and robustness of classical ensembles and deep networks.
  arXiv  Detail & Related papers  (2025-10-08T01:32:26Z)
• Data Efficient Prediction of excited-state properties using Quantum Neural Networks [4.7436936193373604]
  We present a quantum machine learning model that predicts excited-state properties from the molecular ground state.<n>The model comprises a symmetry-invariant quantum neural network and a conventional neural network.<n>It is able to provide accurate predictions with only a few training data points.
  arXiv  Detail & Related papers  (2024-12-12T16:30:23Z)
• Pre-trained Molecular Language Models with Random Functional Group Masking [54.900360309677794]
  We propose a SMILES-based underlineem Molecular underlineem Language underlineem Model, which randomly masking SMILES subsequences corresponding to specific molecular atoms. This technique aims to compel the model to better infer molecular structures and properties, thus enhancing its predictive capabilities.
  arXiv  Detail & Related papers  (2024-11-03T01:56:15Z)
• Analysis of Atom-level pretraining with Quantum Mechanics (QM) data for Graph Neural Networks Molecular property models [0.0]
  We show how atom-level pretraining with quantum mechanics (QM) data can mitigate violations of assumptions regarding the distributional similarity between training and test data. This is the first time that hidden state molecular representations are analyzed to compare the effects of molecule-level and atom-level pretraining on QM data.
  arXiv  Detail & Related papers  (2024-05-23T17:51:05Z)
• Universal neural network potentials as descriptors: Towards scalable chemical property prediction using quantum and classical computers [0.0]
  We present a versatile approach that uses the intermediate information of a universal neural network potential as a general-purpose descriptor for chemical property prediction. We show that transfer learning with graph neural network potentials such as M3GNet and MACE achieves accuracy comparable to state-of-the-art methods for predicting the NMR chemical shifts.
  arXiv  Detail & Related papers  (2024-02-28T15:57:22Z)
• QKSAN: A Quantum Kernel Self-Attention Network [53.96779043113156]
  A Quantum Kernel Self-Attention Mechanism (QKSAM) is introduced to combine the data representation merit of Quantum Kernel Methods (QKM) with the efficient information extraction capability of SAM. A Quantum Kernel Self-Attention Network (QKSAN) framework is proposed based on QKSAM, which ingeniously incorporates the Deferred Measurement Principle (DMP) and conditional measurement techniques. Four QKSAN sub-models are deployed on PennyLane and IBM Qiskit platforms to perform binary classification on MNIST and Fashion MNIST.
  arXiv  Detail & Related papers  (2023-08-25T15:08:19Z)
• QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules [69.25826391912368]
  We generate a new Quantum Hamiltonian dataset, named as QH9, to provide precise Hamiltonian matrices for 999 or 2998 molecular dynamics trajectories. We show that current machine learning models have the capacity to predict Hamiltonian matrices for arbitrary molecules.
  arXiv  Detail & Related papers  (2023-06-15T23:39:07Z)
• Atomic and Subgraph-aware Bilateral Aggregation for Molecular Representation Learning [57.670845619155195]
  We introduce a new model for molecular representation learning called the Atomic and Subgraph-aware Bilateral Aggregation (ASBA) ASBA addresses the limitations of previous atom-wise and subgraph-wise models by incorporating both types of information. Our method offers a more comprehensive way to learn representations for molecular property prediction and has broad potential in drug and material discovery applications.
  arXiv  Detail & Related papers  (2023-05-22T00:56:00Z)
• Molecular Geometry-aware Transformer for accurate 3D Atomic System modeling [51.83761266429285]
  We propose a novel Transformer architecture that takes nodes (atoms) and edges (bonds and nonbonding atom pairs) as inputs and models the interactions among them. Moleformer achieves state-of-the-art on the initial state to relaxed energy prediction of OC20 and is very competitive in QM9 on predicting quantum chemical properties.
  arXiv  Detail & Related papers  (2023-02-02T03:49:57Z)
• Graph neural networks for the prediction of molecular structure-property relationships [59.11160990637615]
  Graph neural networks (GNNs) are a novel machine learning method that directly work on the molecular graph. GNNs allow to learn properties in an end-to-end fashion, thereby avoiding the need for informative descriptors. We describe the fundamentals of GNNs and demonstrate the application of GNNs via two examples for molecular property prediction.
  arXiv  Detail & Related papers  (2022-07-25T11:30:44Z)
• OrbNet: Deep Learning for Quantum Chemistry Using Symmetry-Adapted Atomic-Orbital Features [42.96944345045462]
  textscOrbNet is shown to outperform existing methods in terms of learning efficiency and transferability. For applications to datasets of drug-like molecules, textscOrbNet predicts energies within chemical accuracy of DFT at a computational cost that is thousand-fold or more reduced.
  arXiv  Detail & Related papers  (2020-07-15T22:38:41Z)

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.