AI Paper Atlas

Research map / Label-efficient and robust learning / Test-time adaptation

Meta-SAGE: Scale Meta-Learning Scheduled Adaptation with Guided Exploration for Mitigating Scale Shift on Combinatorial Optimization

Jiwoo Son, Minsu Kim, Hyeonah Kim, Jinkyoo Park

ICML 2023 · Label-efficient and robust learning › Test-time adaptation · approach: Extrapolation and single-sample adaptation · 4 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 Meta-SAGE instead of EASPOMO · CVRP, N=1,000Gap: 3.95% -> 0.683%Improved
Use Meta-SAGE instead of EASSym-NCO · Real-world CVRP, 500 ≤ N < 600Objective: 95,384 -> 94,028Improved
Add scale meta-learning (SML) (ablation)Sym-NCO with test-time adaptation · TSP, N=500Objective: 18.63 -> 17.70Improved
Add locality bias (ablation)Sym-NCO with SML · TSP, N=500Objective: 17.70 -> 17.68Improved
Schedule decay of locality bias (ablation)Sym-NCO with SML and locality bias · TSP, N=500Objective: 17.68 -> 17.67Improved
Schedule SoftMax temperature (ablation)Sym-NCO with SML and scheduled locality bias · TSP, N=500Objective: 17.67 -> 17.22Improved
Add SML to transform the initial embedding (ablation)SAGE · TSP, N=500L1 embedding distance: 8,066.13 -> 7,175.99Improved
Add SML to transform the initial embedding (ablation)SAGE · CVRP, N=500L1 embedding distance: 10,361.51 -> 9,285.22Improved

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