Generating GFlowNets as You Wish with Diffusion Process

Yuxin Li, Wangbo Zhao, Dongwen Tang, jiyao liu, Xiahai Zhuang, Guang Li, Dianbo Liu, Yang You, Kai WangOpenReview 2025 · Submission to ICLR 2025 · Withdrawn · OpenReview

Its authors withdrew this paper, so there is no full text to read or summarize.

Abstract

Generative Flow Networks (GFlowNets) are probabilistic samplers that learn stochastic policies to generate diverse sets of high-reward objects, which is essential in scientific discovery tasks. However, most existing GFlowNets necessitate training, becoming costly as the diversity of GFlowNets expands and trajectory lengths increase. To alleviate this problem, we propose a method to Generate high-performing GFlowNet parameters based on a given model structure, called GenFlowNet. Specifically, we first prepare an autoencoder to extract latent representations of GeFlowNet parameters and reconstruct them. Then, a structure encoder is trained alongside a conditional latent diffusion model to generate the target GFlowNet parameters based on the given structure information. To the best of our knowledge, it is the first exploration to generate parameters of a probabilistic sampler using the diffusion process. It enables us to obtain a new GFlowNet without training, effectively reducing the trial-and-error cost during GFlowNet development. Extensive experiments on diverse structures and tasks validate the superiority and generalizability of our method.
BibTeX
@misc{li2025generating,
  author = {Yuxin Li and Wangbo Zhao and Dongwen Tang and jiyao liu and Xiahai Zhuang and Guang Li and Dianbo Liu and Yang You and Kai Wang},
  title = {{Generating GFlowNets as You Wish with Diffusion Process}},
  year = {2025},
  url = {https://openreview.net/forum?id=8ljEGpXuqB},
  howpublished = {OpenReview},
  note = {Submitted to ICLR 2025},
}
Figure