AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Maximum Independent Set: Self-Training through Dynamic Programming

Lorenzo Brusca, Lars C.P.M. Quaedvlieg, Stratis Skoulakis, Grigorios Chrysos, Volkan Cevher

NeurIPS 2023 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs · 3 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
Add the greedy algorithm's solution to model roll-out estimates (ablation)CMP · RB MISapproximation ratio: 0.770 ± 0.107 -> 0.836 ± 0.083Improved
Add the greedy algorithm's solution to model roll-out estimates (ablation)CMP · COLLAB MISapproximation ratio: 0.990 ± 0.051 -> 0.990 ± 0.049No clear effect
Add the greedy algorithm's solution to model roll-out estimates (ablation)CMP · TWITTER MISapproximation ratio: 0.967 ± 0.083 -> 0.977 ± 0.031Improved
Add the greedy algorithm's solution to model roll-out estimates (ablation)CMP · SPECIAL MISapproximation ratio: 0.996 ± 0.029 -> 0.994 ± 0.035Hurt
Add the greedy algorithm's solution to model roll-out estimates (ablation)Comparator · ER MISapproximation ratio: 0.930 ± 0.068 -> 0.954 ± 0.058Improved
Add the greedy algorithm's solution to model roll-out estimates (ablation)Comparator · BA MISapproximation ratio: 0.922 ± 0.089 -> 0.942 ± 0.055Improved
Add the greedy algorithm's solution to model roll-out estimates (ablation)Comparator · WS MISapproximation ratio: 0.823 ± 0.119 -> 0.831 ± 0.116Improved
Use the DP-inspired self-trained graph comparator instead of neural baselinesMIS solver · RB, COLLAB, TWITTER, SPECIALapproximation ratioImproved

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