Generative Flow Networks for Discrete Probabilistic Modeling

Dinghuai Zhang · Nikolay Malkin · Zhen Liu · Alexandra Volokhova · Aaron Courville · Yoshua Bengio

Hall E #429

Keywords: [ Probabilistic Methods ] [ DL: Algorithms ] [ PM: Bayesian Models and Methods ] [ DL: Generative Models and Autoencoders ]

[ Abstract ]
[ Poster [ Paper PDF
Tue 19 Jul 3:30 p.m. PDT — 5:30 p.m. PDT
Spotlight presentation: Deep Learning
Tue 19 Jul 1:15 p.m. PDT — 2:45 p.m. PDT


We present energy-based generative flow networks (EB-GFN), a novel probabilistic modeling algorithm for high-dimensional discrete data. Building upon the theory of generative flow networks (GFlowNets), we model the generation process by a stochastic data construction policy and thus amortize expensive MCMC exploration into a fixed number of actions sampled from a GFlowNet. We show how GFlowNets can approximately perform large-block Gibbs sampling to mix between modes. We propose a framework to jointly train a GFlowNet with an energy function, so that the GFlowNet learns to sample from the energy distribution, while the energy learns with an approximate MLE objective with negative samples from the GFlowNet. We demonstrate EB-GFN's effectiveness on various probabilistic modeling tasks. Code is publicly available at

Chat is not available.