AutoGAN-DSP: Stabilizing GAN architecture search with deterministic score predictors

Haesung Jo, Changhee Joo

Research output: Contribution to journalArticlepeer-review


Generative Adversarial Network (GAN) has been widely used in many research areas of computer vision, anomaly detection, translation, optimal control, etc. However, in most cases, its network architectures have been hand-picked based on human experiences. To this end, neural Architecture Search (NAS) that automatically finds architectures have attracted much attention to automate the architecture search. In this work, we show that the NAS for Generative Adversarial Network (GAN), also denoted Generative Adversarial Neural Architecture Search (GANAS), often suffers from unstable search due to its innate randomness in the performance evaluation process. We address the stability issue by introducing deterministic score predictors and develop a unified framework to simultaneously conduct the architecture search and the predictor training. Further we develop a novel 2-phase architecture and parameter selection process to balance computational cost and architecture performance. Through extensive experiments, we demonstrate that our proposed AutoGAN-DSP outperforms other RL-based GANAS schemes as well as stabilizing the search performance. Our code and datasets are available on GitHub (

Original languageEnglish
Article number127187
Publication statusPublished - 2024 Mar 7

Bibliographical note

Publisher Copyright:
© 2023 Elsevier B.V.


  • Architecture score prediction
  • Generative Adversarial Networks
  • Neural architecture search
  • Reinforcement learning

ASJC Scopus subject areas

  • Computer Science Applications
  • Cognitive Neuroscience
  • Artificial Intelligence


Dive into the research topics of 'AutoGAN-DSP: Stabilizing GAN architecture search with deterministic score predictors'. Together they form a unique fingerprint.

Cite this