Pith. sign in

REVIEW 2 cited by

Thermodynamics-informed graph neural networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2203.01874 v3 pith:WU6EP4XX submitted 2022-03-03 cs.LG cs.CEmath.DS

classification cs.LGcs.CEmath.DS
keywords learningdeepexamplesgeometricgraphnetworksneuralprovided
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

In this paper we present a deep learning method to predict the temporal evolution of dissipative dynamic systems. We propose using both geometric and thermodynamic inductive biases to improve accuracy and generalization of the resulting integration scheme. The first is achieved with Graph Neural Networks, which induces a non-Euclidean geometrical prior with permutation invariant node and edge update functions. The second bias is forced by learning the GENERIC structure of the problem, an extension of the Hamiltonian formalism, to model more general non-conservative dynamics. Several examples are provided in both Eulerian and Lagrangian description in the context of fluid and solid mechanics respectively, achieving relative mean errors of less than 3% in all the tested examples. Two ablation studies are provided based on recent works in both physics-informed and geometric deep learning.

Discussion (0). Sign in to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Graph Neural Network approach to zero-shot Digital Twins

    cs.LG 2026-07 conditional novelty 5.0 of 10

    A closed-loop vision-plus-physics pipeline simulates previously unseen solids and fluids in real time, continuously nudging the physics engine with camera observations and overlaying inferred stress and velocity field...

  2. Latent Dynamics Graph Convolutional Networks for model order reduction of parameterized time-dependent PDEs

    cs.LG 2026-01 conditional novelty 5.0 of 10

    LD-GCN couples an encoder-free latent-space neural ODE with a graph convolutional decoder, achieving accurate reduced-order modeling of time-dependent parameterized PDEs and detecting bifurcations from the latent traj...

Pith tools