Skip to main content
Search

# Graph Neural Network

40 related articles

Subscribe to updates
  1. arXiv

    GraphMuon retunes GNN updates to graph-propagated features, reaching AdamW's loss target 1.32x to 2.42x faster on three OGB benchmarks

    A GNN weight matrix acts on graph-propagated features, so an update that is well normalized in parameter space can still be amplified by graph structure into a large representation-level perturbation. GraphMuon moves Muon's matrix orthogonalization into a metric defined by the covariance of the propagated layer inputs and scales each step by its induced effect on the layer representation. On three large-scale OGB benchmarks it reaches AdamW's validation-loss target in 1/2.32 to 1/1.32 of the wall-clock time, a 1.32x to 2.42x speedup.

  2. arXiv

    Gravitational-wave solvers get a neural preconditioner: 2 to 15 fewer GMRES iterations than basic ILU in the hardest high-frequency regime

    High-accuracy gravitational-wave source modeling has long avoided machine learning because neural networks carry a noise floor. Researchers trained a graph neural network as a preconditioner for an iterative solver, leaving the traditional GMRES to enforce final accuracy while the network only accelerates convergence. On the high-frequency elliptic equations for asymmetric-mass black hole binaries, the hardest parameter regions need 2 to 15 fewer GMRES iterations than basic ILU and 2 to 4 times less wall time than the next best method.

  3. KEN embeds 2D convolutional kernels in an E(3)-equivariant potential: training energy error reaches 6.93 meV/atom, but test-set force error stays above MACE

    KEN embeds two-dimensional convolutional kernels in an E(3)-equivariant graph neural network so that an interatomic potential reads electronic spin-interaction matrices alongside geometric coordinates, sidestepping the ill-posedness of coordinate-only potentials in strongly correlated magnetic systems. On the HE26 actinide dataset, KENJI reaches a training bonding-energy mean absolute error of 6.93 meV/atom against 44.7 meV/atom for MACE-osaka26, and its training force error of 34.10 meV/Å is on par with 26.30 meV/Å. On the independent test set the energy error is 46.74 meV/atom and the force error exceeds MACE-osaka26, which the authors partly attribute to training without stress.

  4. arXiv

    Brain networks stop sharing one parcellation: IC-GNN predicts autism, Alzheimer's and depression from each person's own community organization

    IC-GNN regroups the same atlas-defined brain regions into discrete, multiscale functional communities for each person, then uses those communities to guide edge refinement and region-specific weights in a graph neural network. Group-level atlases had smoothed over individual differences in community boundaries, while voxel-level individualized parcellations demand long scans and complicate cross-subject comparison. Across more than 30,000 participants in ABIDE, ADNI and the UK Biobank, IC-GNN reached the highest mean AUROC and accuracy among 15 baselines, with AUROC of 75.41% on ABIDE, 86.46% on ADNI and 60.62% on the UK Biobank.

  5. arXiv

    Graph neural networks stop at predictions: GSD turns message passing into readable formulas and recovers expert descriptors in three systems

    Graph neural networks learn structure–property relationships from graphs of atoms and bonds, but those relationships stay in a latent space and are hard to read as scientific rules. Graph symbolic distillation (GSD) first uses a constrained message-passing architecture search to fix how information is transformed, propagated and aggregated, then fits each layer's learned transformation with a sparse symbolic expression while keeping graph connectivity and aggregation. Across halide-perovskite band gaps, molecular hydration free energies and multidentate adsorption on transition-metal surfaces, it rebuilds expert descriptors from elementary node and edge features and yields testable local-geometry, polarity–size and electronic–connectivity relationships.

  6. Solar filament fragments stop being stitched by distance alone: a graph network treats each fragment as a node and reaches AUC 0.867 at kNN 10

    Solar filaments in Hα images break into fragments as they evolve, and projection effects can separate pieces of one filament while bringing pieces of different filaments close together, so distance and orientation alone cannot decide which fragments belong together. The study treats each fragment as a graph node and each candidate pair as an edge, predicts at the edge level with a graph neural network, and replaces conventional additive aggregation with multiplicative aggregation so that inconsistent neighbors contribute less. On a dataset built from about 100 Kanzelhöhe Observatory Hα images and about 1,700 fragments, the method reaches AUC 0.867 and AP 0.792 at kNN 10, above GCN at 0.832/0.747 and GAT at 0.842/0.766.

  7. Graph neural network maps PBE formation energies onto the r2SCAN scale, cutting the cross-functional gap to 14.3 meV/atom

    Formation energies from different exchange-correlation functionals have not been directly mergeable: in MatPES the same structures differ by 107 meV/atom on average between PBE and r2SCAN. Using more than 380,000 structurally paired PBE–r2SCAN entries, researchers trained a graph neural network to predict the energy residual between the two functionals and correct PBE formation energies onto the r2SCAN scale. With GPTFF as the backbone, the model reaches a mean absolute error of 14.3 meV/atom on the held-out test set, below the 18.2 meV/atom of CHGNet.

  8. arXiv

    Gene regulatory network inference stops choosing sides: scGPL fuses global topology with pairwise samples for up to 13.7% AUPRC gain

    Inferring gene regulatory networks from single-cell RNA sequencing has long split into two routes: graph methods train on the whole network as one graph and tend to overfit, while pairwise methods split it into transcription factor–target pairs, gaining abundant samples but losing global topology. scGPL uses a dual-branch design to model both the global regulatory graph and a local subgraph around each candidate pair, reaching the best performance on seven benchmark datasets, with AUPRC up to 13.7% above the strongest baseline.

  9. arXiv

    Transformer neural operators stop flattening local thinning: BiLoGo lifts the rib-region smoothing index from 0.41–0.56 to 0.94

    In sheet-forming simulation, Transformer-based neural operators move information efficiently across the mesh but tend to smooth the localised thinning near deep-drawn corners and reinforcing ribs, the regions that often decide whether a part can be formed. BiLoGo couples local node–element message passing on a bipartite graph with a dual-stream Transformer neural operator, compressing the blank state and the tool contact into separate tokens and keeping local features through gated fusion. On a ribbed hot-stamping case, BiLoGo-U raises the thinning smoothing index near the ribs from 0.41–0.56 for Transformer-based operators to 0.94, and cuts mean positional error by 8.3% relative to the most accurate hierarchical graph network, CAtt-BiUGNN.

  10. arXiv

    Wildfire forecasts move to a 12-hour clock: FireGraphNet's directed graph lifts near-front ranking 1.7–1.9 times a distance rule

    Wildfire decisions are made in hours, yet most learned spread models predict daily on targets that include already burned area. FireGraphNet recasts roughly 12-hour growth as node classification on directed H3 hexagonal graphs: candidates are unburned cells within five rings of the front, edges carry wind alignment, elevation difference, fuel continuity and barriers, and a graph neural network passes messages along those edges. On five sealed California test fires the five variants reach average precision 1.7–1.9 times the strongest distance baseline, and the GINE variant keeps a 1.62-fold advantage out of state.