AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

NN-Baker: A Neural-network Infused Algorithmic Framework for Optimization Problems on Geometric Intersection Graphs

Evan McCarty, Qi Zhao, Anastasios Sidiropoulos, Yusu Wang

NeurIPS 2021 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 2 citations (OpenAlex)

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
wrap TGS in the Baker frameworkTGS · 2D-denseMIS ratio: 0.915 -> 0.936Improved
wrap LwD in the Baker frameworkLwD · 2D-denseMIS ratio: 0.917 -> 0.955Improved
wrap Erdos-GNN in the Baker frameworkErdos-GNN · 2D-denseMIS ratio: 0.834 -> 0.923Improved
wrap Erdos-GNN in the Baker frameworkErdos-GNN · 2DGaussianMIS ratio: 0.769 -> 0.848Improved
wrap LwD in the Baker frameworkLwD · 3DMIS ratio: 0.902 -> 0.954Improved
wrap TGS in the Baker frameworkTGS · Torus-4DMIS ratio: 0.923 -> 0.937Improved
wrap LwD in the Baker frameworkLwD · 2D-sparseMIS ratio: 0.908 -> 0.926Improved
use Erdos-Baker instead of UNet-BakerNN-Baker · 2D-sparseMIS ratio: 0.919 -> 0.917No clear effect
replace KaMIS per-cell solver with NN (UNet-Baker vs K-Baker at similar runtime)K-Baker · 2D-denseMIS ratio: 0.753 -> 0.915Improved
replace exact KaMIS by UNet-BakerKaMIS · 2D-densesolve time (s): 3385.1 -> 18.06Improved
replace UNet with multi-layer fully connected network as Baker component (ablation)UNet-Baker · MISMIS ratio: 70%-80%Hurt
increase graph size without Baker decompositionTGS/LwD/Erdos-GNN · 2D-denseMIS ratioHurt

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