面向GFlowNets部分推断的能量分解学习
Learning Energy Decompositions for Partial Inference of GFlowNets
AI总结：
针对GFlowNet部分推断中中间能量评估成本高、易产生误导信号的问题，提出能量分解学习方法LED-GFN，将能量分解为可学习势函数并重参数化流函数，在五类生成任务上验证了优越性。
摘要：
本文研究生成流网络（GFlowNets），该网络通过一系列动作从玻尔兹曼能量分布中采样对象。我们重点研究通过部分推断改进GFlowNet：即通过评估中间状态或转移来训练流函数。为此，近期开发的前瞻式GFlowNet基于中间状态能量评估对流函数进行重参数化。然而，这类中间能量评估可能存在两个问题：（i）评估成本过高或无法评估；（ii）在动作序列存在大幅能量波动时，甚至会提供误导性的训练信号。为解决该问题，我们提出面向GFlowNets的能量分解学习方法（LED-GFN）。我们的核心思路是：（i）将对象的能量分解为定义在状态转移上的可学习势函数；（ii）利用这些势函数对流函数进行重参数化。具体而言，为生成有信息量的局部信用分配，我们提出对势函数施加正则化，使其在动作序列上平滑变化。值得注意的是，使用我们学习到的势函数训练GFlowNet能够保留最优策略。我们在五个问题（包括无结构集合与最大独立集生成、分子图生成以及RNA序列生成）上通过实验验证了LED-GFN的优越性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
