Mahir Dihan, Rahman Khan, Md Ashrafur, Wasif Jalal, Md Roqunuzzaman, Sojib Mashroor, Hasan Bhuiyan
We lifted 9 functions out of this paper's own repositories and ran 8 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| CIAM-Group/NCO_code | canonical | 5 of 6 |
| wjalal/pomo_beam | canonical | 3 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| augment_xy_data_by_8_fold | Ran | wjalal/pomo_beam/NEW_py_ver/CVRP/POMO/CVRProblemDef.py pointer only (licence: NONE) · get_code("445c20b7977e2393") |
| generate_mcvrp_data | Ran | CIAM-Group/NCO_code/single_objective/DPN-minmaxVRP-master/generate_data.py code served (permissive licence) · get_code("64a6161651451f80") |
| generate_mdvrp_data | Ran | CIAM-Group/NCO_code/single_objective/DPN-minmaxVRP-master/generate_data.py code served (permissive licence) · get_code("4d4bbb51a9c3b93e") |
| generate_mtsp_data | Ran | CIAM-Group/NCO_code/single_objective/DPN-minmaxVRP-master/generate_data.py code served (permissive licence) · get_code("2a833239784ee31c") |
| get_random_problems | Ran | wjalal/pomo_beam/NEW_py_ver/CVRP/POMO/CVRProblemDef.py pointer only (licence: NONE) · get_code("f0b32fbf3b6d4fb4") |
| multi_head_attention | Ran | wjalal/pomo_beam/NEW_py_ver/CVRP/POMO/CVRPModel.py pointer only (licence: NONE) · get_code("6dc103e776ff9eed") |
| multi_head_attention | Ran | CIAM-Group/NCO_code/single_objective/DPN-minmaxVRP-master/nets/attention_model.py code served (permissive licence) · get_code("1e5f092766104b78") |
| reshape_by_heads | Ran | CIAM-Group/NCO_code/single_objective/DPN-minmaxVRP-master/nets/ha_hpa_encoder.py code served (permissive licence) · get_code("459fe521069329c6") |
| get_options | Not yet run | CIAM-Group/NCO_code/multi-objective/MORAM/options.py code served (permissive licence) · get_code("7661feb5a9c80c6b") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Neural Combinatorial Optimization (NCO) has emerged as a powerful framework for solving combinatorial optimization problems by integrating deep learning-based models. This work focuses on improving existing inference techniques to enhance solution quality and generalization. Specifically, we modify the Random Re-Construct (RRC) approach of the Light Encoder Heavy Decoder (LEHD) model by incorporating Simulated Annealing (SA). Unlike the conventional RRC, which greedily replaces suboptimal segments, our SA-based modification introduces a probabilistic acceptance mechanism that allows the model to escape local optima and explore a more diverse solution space. Additionally, we enhance the Policy Optimization with Multiple Optima (POMO) approach by integrating Beam Search, enabling systematic exploration of multiple promising solutions while maintaining diversity in the search space. We further investigate different inference strategies, including Softmax Sampling, Greedy, Gumbel-Softmax, and Epsilon-Greedy, analyzing their impact on solution quality. Furthermore, we explore instance augmentation techniques, such as horizontal and vertical flipping and rotation-based augmentations, to improve model generalization across different CVRP instances. Our extensive experiments demonstrate that these modifications significantly reduce the optimality gap across various Capacitated Vehicle Routing Problem (CVRP) benchmarks, with Beam Search and SA-based RRC consistently yielding superior performance. By refining inference techniques and leveraging enhanced search strategies, our work contributes to the broader applicability of NCO models in real-world combinatorial optimization tasks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2604.16581")
get_code_for_paper("2604.16581")
have("2604.16581")
Connect an agent — have() is free.