An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation
Authors: Honguk Woo, Hyunsung Lee, Sangwoo Cho8666-8674
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate the framework with several COPs such as priority-based task scheduling and multidimensional knapsack, demonstrating the benefits of the framework in terms of inference latency and performance. In this section, we evaluate our framework with multidimensional knapsack problem (MDKP) and global fixed-priority task scheduling (GFPS) (Davis et al. 2016). The problem details including RL formulation, data generation, and model training can be found in Appendix B and C. |
| Researcher Affiliation | Collaboration | Honguk Woo1*, Hyunsung Lee2 , Sangwoo Cho1 1Department of Computer Science and Engineering, Sungkyunkwan University 2Kakao Corporation |
| Pseudocode | Yes | Algorithm 1: Learning-to-rank distillation |
| Open Source Code | No | The paper does not provide an unambiguous statement of releasing the source code for the described methodology, nor does it include a direct link to a code repository. |
| Open Datasets | No | The paper mentions "data generation" and "testing dataset" but does not provide specific access information (link, DOI, formal citation with authors/year, or established benchmark dataset name with attribution) for a publicly available dataset. |
| Dataset Splits | No | The paper mentions "testing dataset" sizes but does not specify exact training, validation, or testing split percentages, absolute sample counts for each split, or reference predefined splits with citations for reproduction. |
| Hardware Specification | No | No specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running experiments were mentioned. |
| Software Dependencies | No | The paper mentions "ORtools" but does not provide specific version numbers for software components or libraries required for reproducibility. |
| Experiment Setup | No | The paper does not contain concrete hyperparameter values, training configurations, or system-level settings in the main text that would allow for detailed experimental setup reproduction. |