cs.LGNov 7, 2026

CONSTRAINER: Promptable Graph-Structured Optimization via Constraint Conditioning

Authors: Zeeshan Memon, Mingke Tian, Xinyuan Song, Hongwei Jin, Kibaek Kim, Liang Zhao

Organizations: Emory University · Argonne National Laboratory · Causal Dynamics Lab

Abstract

Neural methods for graph-structured optimization have achieved strong performance within individual problem classes, but are typically trained for fixed formulations, limiting reuse across related problem variants. Recent progress in foundation models has motivated shared neural backbones trained across multiple graph-structured optimization tasks; however, existing approaches primarily share instance-level representations while treating feasibility constraints implicitly. A key source of shared structure across constrained optimization problems is the constraint set itself, which often exhibits substantial overlap across tasks. We propose CONSTRAINER, a constraint-conditioned framework for graph-structured optimization that treats constraints as structured inputs. Constraint specifications are parsed into operator graphs and encoded using a graph neural network to produce invariant constraint embeddings, which condition a shared backbone model for solution prediction. We evaluate our approach on power grid optimization and mixed-integer linear programming problems, where it shows improved solution optimality and enables efficient transfer learning and generalization compared to baseline methods.

Figures & tables

Appendix figures & tables16 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Graph Optimization Foundation Model: Tokenizing Graph via A Language-Model Paradigm

    Sep 29, 2025Yunhao Liang, Pujun Zhang, Yuan Qu +3Graph SSLCombinatorial Optimization

  2. EnerGNN: Learning Optimization-Compatible Energy Functions for Exact Constrained Combinatorial Inference

    Oct 24, 2026Niki Triantafyllou, Maria M. PapathanasiouCombinatorial OptimizationNeural Combinatorial Optimization