Auto-gas: Automated proxy discovery for training-free generative architecture search

Lujun Li, Haosen Sun, Shiwen Li, Peijie Dong, Wenhan Luo, Wei Xue, Qifeng Liu, Yike Guo

Abstract: In this paper, we introduce Auto-GAS, the first training-free Generative Architecture Search (GAS) framework enabled by an autodiscovered proxy. Generative models like Generative Adversarial Networks (GANs) are now widely used in many real-time applications. Previous GAS methods use differentiable or evolutionary search to find optimal GAN generators for fast inference and memory efficiency. However, the high computational overhead of these training-based GAS techniques limits their adoption. To improve search efficiency, we explore trainingfree GAS but find existing zero-cost proxies designed for classification tasks underperform on generation benchmarks. To address this challenge, we develop a custom proxy search framework tailored for GAS tasks to enhance predictive power. Specifically, we construct an informationaware proxy that takes feature statistics as inputs and utilizes advanced transform, encoding, reduction, and augment operations to represent candidate proxies. Then, we employ an evolutionary algorithm to perform crossover and mutation on superior candidates within the population based on correlation evaluation. Finally, we perform generator search without training using the optimized proxy. Thus, Auto-GAS enables automated proxy discovery for GAS while significantly accelerating the search before training stage. Extensive experiments on image generation and image-to-image translation tasks demonstrate that Auto-GAS strikes superior accuracy-speed tradeoffs over state-of-the-art methods. Remarkably, Auto-GAS achieves competitive scores with 110× faster search than GAN Compression. Code at: https://github.com/lliai/Auto-GAS.