paper-with-me

Papers

Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets

2023-09-21 · NeurIPS 2023 11

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.

📄 PDF Abstract BibTeX

Code (1)

zdhnarsil/gflownet-combopt 공식 구현 pytorch

Tasks

Combinatorial Optimization

Similar Papers 제목 키워드 기반

Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets

2023-09-21

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 Optimization

Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets

2023-05-26 · Dinghuai Zhang, Hanjun Dai, Nikolay Malkin, Aaron Courville 외

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 Optimization

Modern graph neural networks do worse than classical greedy algorithms in solving combinatorial optimization problems like maximum independent set

2022-06-27 · Maria Chiara Angelini, Federico Ricci-Tersenghi

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 Network

Combinatorial Optimization with Automated Graph Neural Networks

2024-06-05 · Yang Liu, Peng Zhang, Yang Gao, Chuan Zhou 외

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 Search

Solving Combinatorial Counting Problems with Weighted First-Order Model Counting

2026-05-24 · Yuanhong Wang, Juhua Pu, Yuxu Zhou, Yuyi Wang 외 arxiv

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…