AI Paper Atlas

Research map / Graph learning / Graph algorithms and clustering

Problem Distributions as Tasks: Repurposing Meta Learning for Generative Combinatorial Optimization towards Multi-task Pretraining and Adaptation

Wenzheng Pan, Jiale Ma, Nuoyan Chen, Yang Li, Junchi Yan

ICML 2026 · Graph learning › Graph algorithms and clustering · approach: Neural combinatorial optimization on graphs

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 OOD fine-tuning on few-shot support data (ablation)M2GenCO · MIS-BA 200-300objective: 65.45 -> 70.01Improved
add OOD fine-tuning on few-shot support data (ablation)M2GenCO · MCut-WS 200-300objective: 795.63 -> 839.47Improved
add OOD fine-tuning on few-shot support data (ablation)M2GenCO · ATSP-SAT-54objective: 5.30 -> 2.31Improved
add few-shot fine-tuning on an unseen task (MVC) (ablation)M2GenCO · MVC-RB-LARGEoptimality gap: 1.16% -> 0.94%Improved
add gradient normalization across task batches (ablation)M2GenCO meta-pretraining · MIS RB-200-300objective: 16.678 -> 16.732Improved
add gradient normalization across task batches (ablation)M2GenCO meta-pretraining · MCut BA-200-300objective: 635.296 -> 657.190Improved
use 5 inner steps instead of 1 (ablation)M2GenCO meta-pretraining · MCut BA-200-300objective: 657.190 -> 632.530Hurt
use 10 inner steps instead of 1 (ablation)M2GenCO meta-pretraining · MCut BA-200-300objective: 657.190 -> 572.754Hurt
add MCl to the task pool (MIS, MCut) (ablation)M2GenCO meta-pretraining · MCl RB-200-300objective: 10.30 -> 11.37Improved
add MIS to the task pool (MCl, MCut) (ablation)M2GenCO meta-pretraining · MIS RB-200-300objective: 14.84 -> 16.33Improved
add MCl to the task pool (MIS, MCut) (ablation)M2GenCO meta-pretraining · MCut BA-200-300objective: 631.13 -> 621.82No clear effect
tune on 10% flipped labels instead of best-quality labels (ablation)M2GenCO fine-tuning · MIS BA-200-300objective: 69.76 -> 69.53No clear effect

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