Research map / Adversarial robustness and security / Black-box and transfer attacks
ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
Han Lu, Zenan Li, Runzhong Wang, Qibing Ren, Xijun Li, Mingxuan Yuan, Jia Zeng, Xiaokang Yang, Junchi Yan
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Remove DAG dependency edges while preserving a no-worse optimum | DAG scheduling solvers, including Tetris · TPC-H-50 | makespan: 0.8227 -> 0.9397 | Hurt |
| Remove DAG dependency edges while preserving a no-worse optimum | Critical Path · TPC-H-100 | makespan: 1.6018 -> 1.7498 | Hurt |
| Remove DAG dependency edges while preserving a no-worse optimum | Tetris · TPC-H-150 | makespan: 2.2469 -> 2.5329 | Hurt |
| Halve selected non-tour edge costs while preserving a no-worse optimum | LKH3 · ATSP, 20 cities | tour length: 1.4595 -> 1.4611 | Hurt |
| Halve selected non-tour edge costs while preserving a no-worse optimum | LKH3 · ATSP, 50 cities | tour length: 1.6621 -> 1.6679 | Hurt |
| Halve selected non-tour edge costs while preserving a no-worse optimum | LKH3 · ATSP, 100 cities | tour length: 1.5763 -> 1.5862 | Hurt |
| Add set-to-element edges while preserving a no-worse optimum | Gurobi · MC, 100-200 | covered weight: 0.7491 -> 0.7409 | Hurt |
| Add set-to-element edges while preserving a no-worse optimum | Gurobi · MC, 150-300 | covered weight: 1.1485 -> 1.1314 | Hurt |
| Add set-to-element edges while preserving a no-worse optimum | Gurobi · MC, 200-400 | covered weight: 1.4889 -> 1.4684 | Hurt |
| Add set-to-black-element edges while preserving a no-worse optimum | Gurobi · MCSCC, 30-150-3K | covered weight: 18.8934 -> 14.2740 | Hurt |
| Add set-to-black-element edges while preserving a no-worse optimum | Gurobi · MCSCC, 60-300-6K | covered weight: 41.1828 -> 36.0432 | Hurt |
| Add set-to-black-element edges while preserving a no-worse optimum | Gurobi · MCSCC, 100-500-10K | covered weight: 49.3296 -> 43.4866 | Hurt |
Closest papers by meaning
- COMBHelper: A Neural Approach to Reduce Search Space for Graph Combinatorial Problems (AAAI 2024 · similarity 0.88)
- Are Graph Neural Networks Optimal Approximation Algorithms? (NeurIPS 2024 · similarity 0.87)
- Geometric Algorithms for Neural Combinatorial Optimization with Constraints (NeurIPS 2025 · similarity 0.87)
- Towards General Algorithm Discovery for Combinatorial Optimization: Learning Symbolic Branching Policy from Bipartite Graph (ICML 2024 · similarity 0.86)
- Bayesian Optimization of Functions over Node Subsets in Graphs (NeurIPS 2024 · similarity 0.86)
- GOAL: A Generalist Combinatorial Optimization Agent Learner (ICLR 2025 · similarity 0.86)
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.
