AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Set2Graph: Learning Graphs From Sets

Hadar Serviansky, Nimrod Segol, Jonathan Shlomi, Kyle Cranmer, Eilam Gross, Haggai Maron, Yaron Lipman

NeurIPS 2020 · Graph learning › Graph algorithms and clustering · approach: Neural and local graph clustering · 15 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
Use global set context rather than independent Siamese element embeddings (ablation)S2G particle partitioning · Bottom-jetsF1: 0.605 -> 0.646Improved
Use global set context rather than independent Siamese element embeddings (ablation)S2G particle partitioning · Charm-jetsF1: 0.728 -> 0.750Improved
Use global set context rather than independent Siamese element embeddings (ablation)S2G particle partitioning · Light-jetsF1: 0.973 -> 0.972No clear effect
Add attention to the DeepSets set encoder (ablation)S2G particle partitioning · Bottom-jetsF1: 0.640 -> 0.646Improved
Add attention to the DeepSets set encoder (ablation)S2G particle partitioning · Charm-jetsF1: 0.743 -> 0.750Improved
Add one set-encoder layer (ablation)S2G particle partitioning · Bottom-jetsF1: 0.649 -> 0.660Improved
Use DeepSets instead of PointNetSeg as the set encoder (ablation)S2G particle partitioning · Bottom-jetsF1: 0.630 -> 0.646Improved
Use two edge-network layers instead of one (ablation)S2G particle partitioning · Bottom-jetsF1: 0.565 -> 0.646Improved
Use full equivariant-basis broadcasting instead of basic broadcasting (ablation)S2G particle partitioning · Bottom-jetsF1: 0.646 -> 0.655No clear effect
Use global set reasoning rather than pairwise Siamese learningS2G · Delaunay, n=50F1: 0.704 -> 0.926Improved
Use global set reasoning rather than pairwise Siamese learningS2G · Convex hull, Gaussian, 30 pointsF1: 0.275 -> 0.707Improved
Apply S2G instead of GNN5Convex-hull prediction · Spherical, 20-100 pointsF1: 0.667 -> 0.535Hurt

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