IID-GAN: an IID Sampling Perspective for Regularizing Mode Collapse

Despite its success, generative adversarial networks (GANs) still suffer from mode collapse, namely the generator can only map latent variables to a partial set of modes of the target distribution. In this paper, we analyze and try to regularize this issue with an independent and identically distributed (IID) sampling perspective and emphasize that holding the IID property for generation for target distribution (i.e. real distribution) can naturally avoid mode collapse. This is based on the basic IID assumption for real data in machine learning. However, though the source samples $\{\mathbf{z}\}$ obey IID, the generations $\{G(\mathbf{z})\}$ may not necessarily be IID from the target distribution. Based on this observation, we propose a necessary condition of IID generation and provide a new loss to encourage the closeness between the inverse source of real data and the Gaussian source in the latent space to regularize the generation to be IID from the target distribution. The logic is that the inverse samples from target data should also be IID in the source distribution. Experiments on both synthetic and real-world data show the effectiveness of our model.