A theory of continuous generative flow networks

2023/01/30 by Salem Lahlou, Lahlou, Salem, Tristan Deleu +15 · 8 citations
Computer Science · #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Generative Adversarial Networks and Image Synthesis #Human Pose and Action Recognition #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · pdf · doi:10.48550/arxiv.2301.12594

openalex publication_date 2023/01/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Generative flow networks (GFlowNets) are amortized variational inference algorithms that are trained to sample from unnormalized target distributions over compositional objects. A key limitation of GFlowNets until this time has been that they are restricted to discrete spaces. We present a theory for generalized GFlowNets, which encompasses both existing discrete GFlowNets and ones with continuous or hybrid state spaces, and perform experiments with two goals in mind. First, we illustrate critical points of the theory and the importance of various assumptions. Second, we empirically demonstrate how observations about discrete GFlowNets transfer to the continuous case and show strong results compared to non-GFlowNet baselines on several previously studied tasks. This work greatly widens the perspectives for the application of GFlowNets in probabilistic inference and various modeling settings.

Cited by

• One-Step Diffusion Samplers via Self-Distillation and Deterministic Flow
• Latent Chain-of-Thought for Visual Reasoning
• Reinforced sequential Monte Carlo for amortised sampling
• Data-to-Energy Stochastic Dynamics
• AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration
• Expert-aided causal discovery of ancestral graphs
• Torsional-GFN: a conditional conformation generator for small molecules
• Posterior Inference in Latent Space for Scalable Constrained Black-box Optimization

Related

• GFlowNets and variational inference
• Investigating Generalization Behaviours of Generative Flow Networks
• Revisiting Non-Acyclic GFlowNets in Discrete Environments
• Generative Flow Networks: a Markov Chain Perspective
• Stochastic Generative Flow Networks