MMCGAN: Generative Adversarial Network with Explicit Manifold Prior
This work addresses a fundamental issue in GANs for researchers and practitioners in generative modeling, though it is incremental as it builds on existing GAN frameworks with a novel prior.
The paper tackles mode collapse and unstable training in Generative Adversarial Networks (GANs) by introducing an explicit manifold prior based on Minimum Manifold Coding (MMC), which encourages a simple and unfolded manifold. Experiments on toy and real datasets show that MMCGAN effectively alleviates mode collapse, stabilizes training, and improves sample quality.
Generative Adversarial Network(GAN) provides a good generative framework to produce realistic samples, but suffers from two recognized issues as mode collapse and unstable training. In this work, we propose to employ explicit manifold learning as prior to alleviate mode collapse and stabilize training of GAN. Since the basic assumption of conventional manifold learning fails in case of sparse and uneven data distribution, we introduce a new target, Minimum Manifold Coding (MMC), for manifold learning to encourage simple and unfolded manifold. In essence, MMC is the general case of the shortest Hamiltonian Path problem and pursues manifold with minimum Riemann volume. Using the standardized code from MMC as prior, GAN is guaranteed to recover a simple and unfolded manifold covering all the training data. Our experiments on both the toy data and real datasets show the effectiveness of MMCGAN in alleviating mode collapse, stabilizing training, and improving the quality of generated samples.