# Evaluating Curriculum Learning Strategies in Neural Combinatorial Optimization

arXiv: https://arxiv.org/abs/2011.06188 · HTML: https://mlsanity.com/paper/2011.06188/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Nov 2020.

## Built on by (most cited first, 19 of 19)

- [Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization](https://mlsanity.com/paper/2205.13209/) (2022)
- [Towards Omni-generalizable Neural Methods for Vehicle Routing Problems](https://mlsanity.com/paper/2305.19587/) (2023)
- [Pareto Set Learning for Neural Multi-objective Combinatorial Optimization](https://mlsanity.com/paper/2203.15386/) (2022)
- [Learning to Solve Travelling Salesman Problem with Hardness-adaptive Curriculum](https://mlsanity.com/paper/2204.03236/) (2022)
- [ASP: Learn a Universal Neural Solver!](https://mlsanity.com/paper/2303.00466/) (2023)
- [On the Generalization of Neural Combinatorial Optimization Heuristics](https://mlsanity.com/paper/2206.00787/) (2022)
- [Human-inspired Perspectives: A Survey on AI Long-term Memory](https://mlsanity.com/paper/2411.00489/) (2024)
- [Generalization in Deep RL for TSP Problems via Equivariance and Local Search](https://mlsanity.com/paper/2110.03595/) (2021)
- [Instance-Conditioned Adaptation for Large-scale Generalization of Neural Routing Solver](https://mlsanity.com/paper/2405.01906/) (2024)
- [Learning to generalize Dispatching rules on the Job Shop Scheduling](https://mlsanity.com/paper/2206.04423/) (2022)
- [Supplementing Recurrent Neural Networks with Annealing to Solve Combinatorial Optimization Problems](https://mlsanity.com/paper/2207.08189/) (2022)
- [Bridging Synthetic and Real Routing Problems via LLM-Guided Instance Generation and Progressive Adaptation](https://mlsanity.com/paper/2511.10233/) (2025)
- [Game-Theoretic Co-Evolution for LLM-Based Heuristic Discovery](https://mlsanity.com/paper/2601.22896/) (2026)
- [Enhancing the Cross-Size Generalization for Solving Vehicle Routing Problems via Continual Learning](https://mlsanity.com/paper/2510.10262/) (2025)
- [A Curriculum-Based Deep Reinforcement Learning Framework for the Electric Vehicle Routing Problem](https://mlsanity.com/paper/2601.15038/) (2026)
- [On Distributional Dependent Performance of Classical and Neural Routing Solvers](https://mlsanity.com/paper/2508.02510/) (2025)
- [Generative Modeling for Robust Deep Reinforcement Learning on the Traveling Salesman Problem](https://mlsanity.com/paper/2508.08718/) (2025)
- [Test-Time Adaptation for Unsupervised Combinatorial Optimization](https://mlsanity.com/paper/2601.21048/) (2026)
- [Curriculum Learning with GNN-based Reinforcement Learning for Job Shop Scheduling](https://mlsanity.com/paper/2609.28085/) (2026)

## Abstract (arXiv)

Neural combinatorial optimization (NCO) aims at designing problem-independent and efficient neural network-based strategies for solving combinatorial problems. The field recently experienced growth by successfully adapting architectures originally designed for machine translation. Even though the results are promising, a large gap still exists between NCO models and classic deterministic solvers, both in terms of accuracy and efficiency. One of the drawbacks of current approaches is the inefficiency of training on multiple problem sizes. Curriculum learning strategies have been shown helpful in increasing performance in the multi-task setting. In this work, we focus on designing a curriculum learning-based training procedure that can help existing architectures achieve competitive performance on a large range of problem sizes simultaneously. We provide a systematic investigation of several training procedures and use the insights gained to motivate application of a psychologically-inspired approach to improve upon the classic curriculum method.