Improving Generative Flow Networks with Path Regularization

09/29/2022
by   Anh Do, et al.
12

Generative Flow Networks (GFlowNets) are recently proposed models for learning stochastic policies that generate compositional objects by sequences of actions with the probability proportional to a given reward function. The central problem of GFlowNets is to improve their exploration and generalization. In this work, we propose a novel path regularization method based on optimal transport theory that places prior constraints on the underlying structure of the GFlowNets. The prior is designed to help the GFlowNets better discover the latent structure of the target distribution or enhance its ability to explore the environment in the context of active learning. The path regularization controls the flow in GFlowNets to generate more diverse and novel candidates via maximizing the optimal transport distances between two forward policies or to improve the generalization via minimizing the optimal transport distances. In addition, we derive an efficient implementation of the regularization by finding its closed form solutions in specific cases and a meaningful upper bound that can be used as an approximation to minimize the regularization term. We empirically demonstrate the advantage of our path regularization on a wide range of tasks, including synthetic hypergrid environment modeling, discrete probabilistic modeling, and biological sequence design.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/08/2017

Generative Autotransporters

In this paper, we aim to introduce the classic Optimal Transport theory ...
research
05/24/2023

Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport

Optimal Transport (OT) problem investigates a transport map that bridges...
research
06/09/2020

The statistical effect of entropic regularization in optimal transportation

We propose to tackle the problem of understanding the effect of regulari...
research
08/29/2019

Potential Flow Generator with L_2 Optimal Transport Regularity for Generative Models

We propose a potential flow generator with L_2 optimal transport regular...
research
04/26/2017

Quadratically-Regularized Optimal Transport on Graphs

Optimal transportation provides a means of lifting distances between poi...
research
11/02/2022

Instance-Dependent Generalization Bounds via Optimal Transport

Existing generalization bounds fail to explain crucial factors that driv...
research
11/17/2021

GFlowNet Foundations

Generative Flow Networks (GFlowNets) have been introduced as a method to...

Please sign up or login with your details

Forgot password? Click here to reset