mlsanityData to 14 Oct 2026

GOAL: Graph-based Objective-Aligned Diffusion Solvers for Dynamic Multi-Objective Optimization

arXiv 2605.19119 ↗First posted 18 May 2026cs.NE cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Existing neural combinatorial optimization solvers frame solution search as imitation of optimal decisions, inherently limiting their utility to single-objective minimization and static constraints. We propose GOAL, a conditioned diffusion solver over relational graph representations that enables controllable decision generations by conditioning on human-specified objectives. We introduce a heterogeneous graph encoding in which distinct edge types, corresponding to different classes of constraints, define the message passing structure of the graph neural network, which allows information to propagate selectively according to the ontology of each constraint. GOAL is instantiated and evaluated on three canonical scheduling benchmarks of various constraint complexity: the Flow Shop Problem (FSP), the Job Shop Scheduling Problem (JSP), and the Flexible Job Shop Scheduling Problem (FJSP). Generalization is demonstrated across structurally distinct constraint regimes and problem types without architectural modification. On all three benchmarks, GOAL achieves 100% solution feasibility and near-zero MAPE (below 0.20%) on multiple objectives for problem sizes up to 20 jobs and 60 operations, outperforming NSGA-II and MOEA/D in both solution quality and inference speed by up to 25x.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 48 of its 81 references that are in the map. First posted on arXiv 18 May 2026.

Builds on

48 of 81 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2020Denoising Diffusion Implicit Modelscited by 9,781
  6. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  7. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  8. 2017Inductive Representation Learning on Large Graphscited by 6,320
  9. 2022Classifier-Free Diffusion Guidancecited by 5,847
  10. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  11. 2016Gaussian Error Linear Units (GELUs)cited by 3,502
  12. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
36 more
  1. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,333
  2. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  4. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  5. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 942
  6. 2015Pointer Networkscited by 895
  7. 2018Multi-Task Learning as Multi-Objective Optimizationcited by 821
  8. 2022A Generalist Agentcited by 808
  9. 2015Gated Graph Sequence Neural Networkscited by 796
  10. 2018Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizoncited by 623
  11. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  12. 2018Reinforcement Learning for Solving the Vehicle Routing Problemcited by 333
  13. 2016Cooperative Inverse Reinforcement Learningcited by 300
  14. 2019An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problemcited by 269
  15. 2021SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimizationcited by 230
  16. 2019Pareto Multi-Task Learningcited by 224
  17. 2023DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimizationcited by 221
  18. 2021DC3: A learning method for optimization with hard constraintscited by 184
  19. 2022Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Qualitycited by 182
  20. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 164
  21. 2021Embodied Intelligence via Learning and Evolutioncited by 163
  22. 2020Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learningcited by 140
  23. 2020Learning the Pareto Front with Hypernetworkscited by 125
  24. 2021Learning to Delegate for Large-scale Vehicle Routingcited by 109
  25. 2021Efficient Active Search for Combinatorial Optimization Problemscited by 100
  26. 2023Diffusion Models for Black-Box Optimizationcited by 76
  27. 2021CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraintscited by 49
  28. 2025Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimizationcited by 45
  29. 2020Learning to Solve Combinatorial Optimization Problems on Real-World Graphs in Linear Timecited by 39
  30. 2021ScheduleNet: Learn to solve multi-agent scheduling problems with reinforcement learningcited by 31
  31. 2024Diffusion Model for Data-Driven Black-Box Optimizationcited by 24
  32. 2024Self-Labeling the Job Shop Scheduling Problemcited by 23
  33. 2024DiffSG: A Generative Solver for Network Optimization with Diffusion Modelcited by 14
  34. 2024LLMs can Schedulecited by 11
  35. 2024Expensive Multi-Objective Bayesian Optimization Based on Diffusion Modelscited by 10
  36. 2025Discovering Heuristics with Large Language Models (LLMs) for Mixed-Integer Programs: Single-Machine Schedulingcited by 4

Built on by

Not cited yet.