AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Condition-Aware Graph Flow Matching for Modeling the Distributions of Complex Fluid Systems

Xiaochao Deng, Jie Chen, Xiaogang Deng

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Diffusion-based graph generation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add hierarchical multilevel message passing (HieraGraphNet) (ablation)CGFM · Wing (3D)graph-wise Wasserstein-2: 3.5026 -> 1.9265Improved
add hierarchical message passing (ablation)CGFM · Wing (3D)R2: 0.9712 -> 0.9896Improved
use topology- and geometry-aware coarsening instead of Guillard coarsening (ablation)CGFM · Wing (3D)node-wise Wasserstein-2: 0.0141 -> 0.0099Improved
use TGC instead of Guillard coarsening (ablation)CGFM · Wing (3D)graph-wise Wasserstein-2: 2.3697 -> 1.9265Improved
use TGC instead of Guillard coarsening on TandemFoilSet (ablation)CGFM · TandemFoilSet CruiseAOA=5distribution/sample accuracyImproved
increase number of hierarchy levels (ablation)CGFM · Wing (3D)R2, W2 distancesImproved
reduce number of inference steps (ablation)CGFM · Wing (3D)node-wise Wasserstein-2No clear effect
reduce number of states per training trajectory (ablation)CGFM · Ellipse-InDistdistributional errorNo clear effect
use flow matching with hierarchical graph instead of DDPM-based DGNCGFM vs DGN · Wing (3D)inference time (s/sample): 0.1377 -> 0.0981Improved
sample from learned distribution on GPU instead of numerical solverCGFM · Wing (3D), 3,000 samplesspeed-up over solver: 16.05x (CPU), 606.11x (GPU)Improved
use deterministic model (MuGS-GNN) instead of generative modelMuGS-GNN · Ellipse-InDistgraph-wise Wasserstein-2: 0.9727 vs 0.2734 (CGFM)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy