A deep instance generative framework for milp solvers under limited data availability

Z Geng, X Li, J Wang, X Li… - Advances in Neural …, 2024 - proceedings.neurips.cc
In the past few years, there has been an explosive surge in the use of machine learning (ML)
techniques to address combinatorial optimization (CO) problems, especially mixed-integer …

Learning Backdoors for Mixed Integer Programs with Contrastive Learning

J Cai, T Huang, B Dilkina - arxiv preprint arxiv:2401.10467, 2024 - arxiv.org
Many real-world problems can be efficiently modeled as Mixed Integer Programs (MIPs) and
solved with the Branch-and-Bound method. Prior work has shown the existence of MIP …

Solving combinatorial optimization problems with deep neural network: A survey

F Wang, Q He, S Li - Tsinghua Science and Technology, 2024 - ieeexplore.ieee.org
Combinatorial Optimization Problems (COPs) are a class of optimization problems that are
commonly encountered in industrial production and everyday life. Over the last few decades …

SymILO: A symmetry-aware learning framework for integer linear optimization

Q Chen, T Zhang, L Yang, Q Han, A Wang… - arxiv preprint arxiv …, 2024 - arxiv.org
Integer linear programs (ILPs) are commonly employed to model diverse practical problems
such as scheduling and planning. Recently, machine learning techniques have been …

RL-MILP Solver: A reinforcement learning approach for solving mixed-integer linear programs with graph neural networks

TH Lee, MS Kim - arxiv preprint arxiv:2411.19517, 2024 - arxiv.org
Mixed-Integer Linear Programming (MILP) is an optimization technique widely used in
various fields. Primal heuristics, which reduce the search space of MILP, have enabled …

MGMatch: Fast Matchmaking with Nonlinear Objective and Constraints via Multimodal Deep Graph Learning

Y Sun, K Wang, Z Hu, R Wu, Y Wu, W Song… - Proceedings of the 30th …, 2024 - dl.acm.org
As a core problem of online games, matchmaking is to assign players into multiple teams to
maximize their gaming experience. With the rapid development of game industry, it is …

Scalable Primal Heuristics Using Graph Neural Networks for Combinatorial Optimization

F Cantürk, T Varol, R Aydoğan, OÖ Özener - Journal of Artificial Intelligence …, 2024 - jair.org
By examining the patterns of solutions obtained for various instances, one can gain insights
into the structure and behavior of combinatorial optimization (CO) problems and develop …

GDPlan: Generative Network Planning via Graph Diffusion Model

N Kan, S Yan, J Zou, W Dai, X Gao… - IEEE Transactions on …, 2025 - ieeexplore.ieee.org
Network planning is crucial to facilitate network service under limited network operation
costs. However, adapting the network topology (ie, connections and capacities for physical …

Multi-task Representation Learning for Mixed Integer Linear Programming

J Cai, T Huang, B Dilkina - arxiv preprint arxiv:2412.14409, 2024 - arxiv.org
Mixed Integer Linear Programs (MILPs) are highly flexible and powerful tools for modeling
and solving complex real-world combinatorial optimization problems. Recently, machine …

Efficient Rectification of Neuro-Symbolic Reasoning Inconsistencies by Abductive Reflection

WC Hu, WZ Dai, Y Jiang, ZH Zhou - arxiv preprint arxiv:2412.08457, 2024 - arxiv.org
Neuro-Symbolic (NeSy) AI could be regarded as an analogy to human dual-process
cognition, modeling the intuitive System 1 with neural networks and the algorithmic System 2 …