atlas

Research map / Graph learning / Graph algorithms and clustering

Separate but Equal: Equality in Belief Propagation for Single Cycle Graphs

AAAI 2023 · Graph learning › Graph algorithms and clustering · approach: Graph comparison and random features · 1 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 small random unary costs as tie-breakersMin-sum on single-cycle graphs that oscillate · Single cyclebelief equalityNo clear effect
Add small random unary costs as tie-breakersMin-sum on single-cycle graphs that oscillate · Single cycleassignment equalityNo clear effect
Use random unary costsMin-sum on non-convergent single-cycle instances · Single cycle, 3–5 variables and domain sizes 2–5cases with assignment equality: 96; 98; 96; 97; 96; 96; 81; 94; 99; 84; 92; 96Mixed
Increase cycle sizeMin-sum with random unary costs · Single cycle, domain sizes 2–5instances generated until 100 non-convergent cases: 2240; 5297; 10000+Hurt
Increase domain sizeMin-sum with random unary costs · Single cycle, 3–5 variablesinstances generated until 100 non-convergent cases: 2240; 837; 734; 414Helped
Use random unary costsMin-sum on acyclic graphs · Acyclic graphsbelief equalityHelped

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