mlsanityData to 14 Oct 2026

Collaboration! Towards Robust Neural Methods for Routing Problems

arXiv 2410.04968 ↗First posted 7 Oct 2024cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Despite enjoying desirable efficiency and reduced reliance on domain expertise, existing neural methods for vehicle routing problems (VRPs) suffer from severe robustness issues -- their performance significantly deteriorates on clean instances with crafted perturbations. To enhance robustness, we propose an ensemble-based Collaborative Neural Framework (CNF) w.r.t. the defense of neural VRP methods, which is crucial yet underexplored in the literature. Given a neural VRP method, we adversarially train multiple models in a collaborative manner to synergistically promote robustness against attacks, while boosting standard generalization on clean instances. A neural router is designed to adeptly distribute training instances among models, enhancing overall load balancing and collaborative efficacy. Extensive experiments verify the effectiveness and versatility of CNF in defending against various attacks across different neural VRP methods. Notably, our approach also achieves impressive out-of-distribution generalization on benchmark instances.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 73 of its 93 references that are in the map. First posted on arXiv 7 Oct 2024.

Builds on

73 of 93 references.

References · 73

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
  5. 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  7. 2015Pointer Networkscited by 895
  8. 2018Robustness May Be at Odds with Accuracycited by 880
  9. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  10. 2019Universal Adversarial Triggers for Attacking and Analyzing NLPcited by 722
  11. 2018Attention, Learn to Solve Routing Problems!cited by 656
  12. 2018Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizoncited by 623
38 more
  1. 2016Neural Combinatorial Optimization with Reinforcement Learningcited by 608
  2. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 561
  3. 2017Robust Adversarial Reinforcement Learningcited by 451
  4. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  5. 2020POMO: Policy Optimization with Multiple Optima for Reinforcement Learningcited by 348
  6. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 337
  7. 2018Reinforcement Learning for Solving the Vehicle Routing Problemcited by 333
  8. 2019An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problemcited by 269
  9. 2023DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimizationcited by 221
  10. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  11. 2018Learning a SAT Solver from Single-Bit Supervisioncited by 200
  12. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  13. 2018Learning to Perform Local Rewriting for Combinatorial Optimizationcited by 185
  14. 2018Disentangling Adversarial Robustness and Generalizationcited by 172
  15. 2019Learning Improvement Heuristics for Solving Routing Problemscited by 164
  16. 2020Generalize a Small Pre-trained Model to Arbitrarily Large TSP Instancescited by 162
  17. 2020Understanding and Mitigating the Tradeoff Between Robustness and Accuracycited by 149
  18. 2023Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalizationcited by 142
  19. 2020Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learningcited by 140
  20. 2022DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problemscited by 129
  21. 2020Hybrid Genetic Search for the CVRP: Open-Source Implementation and SWAP* Neighborhoodcited by 125
  22. 2022Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimizationcited by 119
  23. 2021Learning to Delegate for Large-scale Vehicle Routingcited by 109
  24. 2021Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformercited by 108
  25. 2021NeuroLKH: Combining Deep Learning Model with Lin-Kernighan-Helsgaun Heuristic for Solving the Traveling Salesman Problemcited by 103
  26. 2020Learning 2-opt Heuristics for the Traveling Salesman Problem via Deep Reinforcement Learningcited by 100
  27. 2021Efficient Active Search for Combinatorial Optimization Problemscited by 100
  28. 2021Robustness of Graph Neural Networks at Scalecited by 100
  29. 2021Deep Policy Dynamic Programming for Vehicle Routing Problemscited by 94
  30. 2021Matrix Encoding Networks for Neural Combinatorial Optimizationcited by 91
  31. 2023GLOP: Learning Global Partition and Local Construction for Solving Large-scale Routing Problems in Real-timecited by 85
  32. 2023BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimizationcited by 82
  33. 2023Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Optcited by 81
  34. 2023DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimizationcited by 78
  35. 2020DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensemblescited by 73
  36. 2023RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmarkcited by 71
  37. 2024MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Expertscited by 70
  38. 2019Improving Adversarial Robustness of Ensembles with Diversity Trainingcited by 69

50 most cited of 73 All 73 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 6.

9 papers.

  1. 2025BOPO: Neural Combinatorial Optimization via Best-anchored and Objective-guided Preference Optimizationcited by 14
  2. 2025TuneNSearch: a hybrid transfer learning and local search approach for solving vehicle routing problemscited by 2
  3. 2026Chain-of-Context Learning: Dynamic Constraint Understanding for Multi-Task VRPscited by 2
  4. 2025Latent Guided Sampling for Combinatorial Optimizationcited by 0
  5. 2026Adversarial Instance Generation and Robust Training for Neural Combinatorial Optimization with Multiple Objectivescited by 0
  6. 2026Rethinking Efficiency in Neural Combinatorial Optimization: Batched Preference Optimization with Mambacited by 0
  7. 2026FiLMMeD: Feature-wise Linear Modulation for Cross-Problem Multi-Depot Vehicle Routingcited by 0
  8. 2026LINC: Decoupling Local Consequence Scoring from Hidden Matching in Constructive Neural Routingcited by 0
  9. 2026RAISE: LLM-based Automated Heuristic Design with Robust Adversary Instance Searchcited by 0