Ant Colony Sampling with GFlowNets for Combinatorial Optimization
We present the Generative Flow Ant Colony Sampler (GFACS), a novel meta-heuristic method that hierarchically combines amortized inference and parallel stochastic search. Our method first leverages Generative Flow Networks (GFlowNets) to amortize a \emph{multi-modal} prior distribution over combinatorial solution space that encompasses both high-reward and diversified solutions. This prior is iteratively updated via parallel stochastic search in the spirit of Ant Colony Optimization (ACO), leading to the posterior distribution that generates near-optimal solutions. Extensive experiments across seven combinatorial optimization problems demonstrate GFACS's promising performances.
Code (2)
Tasks
Combinatorial OptimizationSimilar Papers 제목 키워드 기반
Let 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 OptimizationLet 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 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 OptimizationExploring Multiple High-Scoring Subspaces in Generative Flow Networks
As a probabilistic sampling framework, Generative Flow Networks (GFlowNets) show strong potential for constructing complex combinatorial objects through the sequential composition of elementary components. However, exist…
An Empirical Study of the Effectiveness of Using a Replay Buffer on Mode Discovery in GFlowNets
Reinforcement Learning (RL) algorithms aim to learn an optimal policy by iteratively sampling actions to learn how to maximize the total expected return, $R(x)$. GFlowNets are a special class of algorithms designed to ge…
Drug DiscoveryReinforcement Learning (RL)