This paper studies generative flow networks (GFlowNets) to sample objects
from the Boltzmann energy distribution via a sequence of actions. In
particular, we focus on improving GFlowNet with partial inference: training
flow functions with the evaluation of the intermediate states or transitions.
To this end, the recently developed forward-looking GFlowNet reparameterizes
the flow functions based on evaluating the energy of intermediate states.
However, such an evaluation of intermediate energies may (i) be too expensive
or impossible to evaluate and (ii) even provide misleading training signals
under large energy fluctuations along the sequence of actions. To resolve this
issue, we propose learning energy decompositions for GFlowNets (LED-GFN). Our
main idea is to (i) decompose the energy of an object into learnable potential
functions defined on state transitions and (ii) reparameterize the flow
functions using the potential functions. In particular, to produce informative
local credits, we propose to regularize the potential to change smoothly over
the sequence of actions. It is also noteworthy that training GFlowNet with our
learned potential can preserve the optimal policy. We empirically verify the
superiority of LED-GFN in five problems including the generation of
unstructured and maximum independent sets, molecular graphs, and RNA sequences.

通过提出的 LED-GFN 模型，该研究论文在五个问题中对生成流网络进行了实证验证，包括无结构和最大独立集的生成，分子图以及 RNA 序列。

学习能量分解用于 GFlowNets 的部分推理

Learning Energy Decompositions for Partial Inference of GFlowNets

In this paper, we examine the problem of partial inference in the context of
structured prediction. Using a generative model approach, we consider the task
of maximizing a score function with unary and pairwise potentials in the space
of labels on graphs. Employing a two-stage convex optimization algorithm for
label recovery, we analyze the conditions under which a majority of the labels
can be recovered. We introduce a novel perspective on the Karush-Kuhn-Tucker
(KKT) conditions and primal and dual construction, and provide statistical and
topological requirements for partial recovery with provable guarantees.

本文探讨了结构化预测中的部分推断问题，采用生成模型方法，考虑在图形标签空间中最大化一种包括一元和成对潜势的评分函数，采用两阶段凸优化算法进行标签恢复，并提供了可证明保证部分恢复的统计和拓扑要求。