Hamiltonian Graph Inference Networks: Joint structure discovery and dynamics prediction for lattice Hamiltonian systems from trajectory data

• URL: http://arxiv.org/abs/2604.23606v1
• Date: Sun, 26 Apr 2026 08:37:10 GMT
• Title: Hamiltonian Graph Inference Networks: Joint structure discovery and dynamics prediction for lattice Hamiltonian systems from trajectory data
• Abstract summary: We introduce the Hamiltonian Graph Inference Network (HGIN)<n>HGIN predicts long-time trajectories from state data alone, for both separable and non-separable Hamiltonians.<n>On three benchmarks, HGIN reduces long-time energy prediction error and trajectory prediction error by six to thirteen orders of magnitude relative to baselines.
• Score: 0.26097841018267615
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Lattice Hamiltonian systems underpin models across condensed matter, nonlinear optics, and biophysics, yet learning their dynamics from data is obstructed by two unknowns: the interaction topology and whether node dynamics are homogeneous. Existing graph-based approaches either assume the graph is given or, as in $α$-separable graph Hamiltonian network, infer it only for separable Hamiltonians with homogeneous node dynamics. We introduce the Hamiltonian Graph Inference Network (HGIN), which jointly recovers the interaction graph and predicts long-time trajectories from state data alone, for both separable and non-separable Hamiltonians and under heterogeneous node dynamics. HGIN couples a structure-learning module -- a learnable weighted adjacency matrix trained under a Hamilton's-equations loss -- with a trajectory-prediction module that partitions edges into physically distinct subgraphs via $k$-means clustering, assigning each subgraph its own encoder and thereby breaking the parameter-sharing bottleneck of conventional GNNs. On three benchmarks -- a Klein--Gordon lattice with long-range interactions and two discrete nonlinear Schrödinger lattices (homogeneous and heterogeneous) -- HGIN reduces long-time energy prediction error and trajectory prediction error by six to thirteen orders of magnitude relative to baselines. A symmetry argument on the Hamiltonian loss further shows that the learned weights encode the parity of the underlying pair potential, yielding an interpretable readout of the system's interaction structure.

Related papers

• Phase space integrity in neural network models of Hamiltonian dynamics: A Lagrangian descriptor approach [0.0]
  We propose Lagrangian Descriptors (LDs) as a diagnostic framework for evaluating neural network models of Hamiltonian systems.<n>By constructing probability density functions weighted by LD values, we embed geometric information into a statistical framework suitable for information-theoretic comparison.<n>For the three-mode nonlinear Schrdinger equation, however, clear differences emerge: symplectic architectures preserve energy but distort phase-space topology, while Reservoir Computing, despite lacking explicit physical constraints, reproduces the homoclinic structure with high fidelity.
  arXiv  Detail & Related papers  (2026-04-01T04:34:54Z)
• Furthering Free-Fermion Findability From Fratricides [0.0]
  We present a novel graph-theoretic approach to simplifying generic many-body Hamiltonians.<n>Our approach expands the class of models that can be mapped to non-interacting fermionic Hamiltonians.<n>This framework provides new insights into Hamiltonian simplification techniques, free-fermion solutions, and group-theoretical characterizations relevant for quantum chemistry, condensed matter physics, and quantum computation.
  arXiv  Detail & Related papers  (2025-09-11T01:56:38Z)
• Graph theory and tunable slow dynamics in quantum East Hamiltonians [0.0]
  We show how graph theory concepts can provide an insight into the origin of slow dynamics in systems with kinetic constraints.<n>Slow dynamics is related to the presence of strong hierarchies between nodes on the Fock-space graph.<n>We numerically demonstrate how these detunings affect the degree of non-ergodicity on finite systems.
  arXiv  Detail & Related papers  (2025-04-04T14:08:18Z)
• Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks [55.227976642410766]
  dynamics of information diffusion within graphs is a critical open issue that heavily influences graph representation learning.<n>Motivated by this, we introduce (port-)Hamiltonian Deep Graph Networks.<n>We reconcile under a single theoretical and practical framework both non-dissipative long-range propagation and non-conservative behaviors.
  arXiv  Detail & Related papers  (2024-05-27T13:36:50Z)
• HeNCler: Node Clustering in Heterophilous Graphs via Learned Asymmetric Similarity [48.62389920549271]
  HeNCler learns a similarity graph by optimizing a clustering-specific objective based on weighted kernel singular value decomposition.<n>Our approach enables spectral clustering on an asymmetric similarity graph, providing flexibility for both directed and undirected graphs.
  arXiv  Detail & Related papers  (2024-05-27T11:04:05Z)
• Coarse-Graining Hamiltonian Systems Using WSINDy [0.0]
  We show that WSINDy can successfully identify a reduced Hamiltonian system in the presence of large intrinsics. WSINDy naturally preserves the Hamiltonian structure by restricting to a trial basis of Hamiltonian vector fields. We also provide a contribution to averaging theory by proving that first-order averaging at the level of vector fields preserves Hamiltonian structure in nearly-periodic Hamiltonian systems.
  arXiv  Detail & Related papers  (2023-10-09T17:20:04Z)
• Applications of Machine Learning to Modelling and Analysing Dynamical Systems [0.0]
  We propose an architecture which combines existing Hamiltonian Neural Network structures into Adaptable Symplectic Recurrent Neural Networks. This architecture is found to significantly outperform previously proposed neural networks when predicting Hamiltonian dynamics. We show that this method works efficiently for single parameter potentials and provides accurate predictions even over long periods of time.
  arXiv  Detail & Related papers  (2023-07-22T19:04:17Z)
• Dynamic Causal Explanation Based Diffusion-Variational Graph Neural Network for Spatio-temporal Forecasting [60.03169701753824]
  We propose a novel Dynamic Diffusion-al Graph Neural Network (DVGNN) fortemporal forecasting. The proposed DVGNN model outperforms state-of-the-art approaches and achieves outstanding Root Mean Squared Error result.
  arXiv  Detail & Related papers  (2023-05-16T11:38:19Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification [59.06717774425588]
  We propose the Explicit Pairwise Factorized Graph Neural Network (EPFGNN), which models the whole graph as a partially observed Markov Random Field. It contains explicit pairwise factors to model output-output relations and uses a GNN backbone to model input-output relations. We conduct experiments on various datasets, which shows that our model can effectively improve the performance for semi-supervised node classification on graphs.
  arXiv  Detail & Related papers  (2021-07-27T19:47:53Z)
• Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification [50.83222170524406]
  We study the intrinsic difficulty in graph classification under the unified concept of resolution dilemmas'' We propose SLIM'', an inductive neural network model for Structural Landmarking and Interaction Modelling.
  arXiv  Detail & Related papers  (2020-06-29T01:01:42Z)
• Multipole Graph Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data. We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity. Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
  arXiv  Detail & Related papers  (2020-06-16T21:56:22Z)

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.