Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.19497 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912856418549760 |
|---|---|
| author | Liao, Yiqiao Koushanfar, Farinaz Naghizadeh, Parinaz |
| author_facet | Liao, Yiqiao Koushanfar, Farinaz Naghizadeh, Parinaz |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19497 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning for Dynamic Combinatorial Optimization without Training Data Liao, Yiqiao Koushanfar, Farinaz Naghizadeh, Parinaz Machine Learning 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. |
| title | Learning for Dynamic Combinatorial Optimization without Training Data |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2505.19497 |