We introduce DyCO-GNN, a novel unsupervised learning framework for Dynamic Combinatorial Optimization that requires no training data beyond the problem instance itself. DyCO-GNN leverages structural similarities across time-evolving graph snapshots to accelerate optimization while maintaining solution quality. We evaluate DyCO-GNN on dynamic maximum cut, maximum independent set, and the traveling salesman problem across diverse datasets of varying sizes, demonstrating its superior performance under tight and moderate time budgets. DyCO-GNN consistently outperforms the baseline methods, achieving high-quality solutions up to 3-60x faster, highlighting its practical effectiveness in rapidly evolving resource-constrained settings.
@article{arxiv.2505.19497,
title = {Learning for Dynamic Combinatorial Optimization without Training Data},
author = {Yiqiao Liao and Farinaz Koushanfar and Parinaz Naghizadeh},
journal= {arXiv preprint arXiv:2505.19497},
year = {2026}
}