Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets
Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning methods. The highly structured constraints in these problems can hinder either optimization or sampling directly in the solution space. On the other hand, GFlowNets have recently emerged as a powerful machinery to efficiently sample from composite unnormalized densities sequentially and have the potential to amortize such solution-searching processes in CO, as well as generate diverse solution candidates. In this paper, we design Markov decision processes (MDPs) for different combinatorial problems and propose to train conditional GFlowNets to sample from the solution space. Efficient training techniques are also developed to benefit long-range credit assignment. Through extensive experiments on a variety of different CO tasks with synthetic and realistic data, we demonstrate that GFlowNet policies can efficiently find high-quality solutions. Our implementation is open-sourced at https://github.com/zdhNarsil/GFlowNet-CombOpt.
Code (1)
Tasks
Combinatorial OptimizationSimilar Papers 제목 키워드 기반
Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets
Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning methods. The highly structured constraints in these problems …
Combinatorial OptimizationLet the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets
Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning methods. The highly structured constraints in these problems …
Combinatorial OptimizationModern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent set
The recent work ``Combinatorial Optimization with Physics-Inspired Graph Neural Networks'' [Nat Mach Intell 4 (2022) 367] introduces a physics-inspired unsupervised Graph Neural Network (GNN) to solve combinatorial optim…
Combinatorial OptimizationGraph Neural NetworkCombinatorial Optimization with Automated Graph Neural Networks
In recent years, graph neural networks (GNNs) have become increasingly popular for solving NP-hard combinatorial optimization (CO) problems, such as maximum cut and maximum independent set. The core idea behind these met…
Combinatorial OptimizationGraph EmbeddingGraph LearningNeural Architecture SearchSolving Combinatorial Counting Problems with Weighted First-Order Model Counting
Combinatorial counting problems pervade artificial intelligence, statistics, and discrete mathematics. Whether the task is enumerating subsets, multisets, permutations, partitions, or compositions under structural and ar…