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

翻译：尽管生成对抗网络（GAN）取得了成功，但仍面临模式崩溃问题，即生成器只能将潜在变量映射到目标分布的部分模式集合。本文从独立同分布（IID）采样视角分析并正则化该问题，强调保持生成过程相对于目标分布的IID属性可自然避免模式崩溃。该论点基于机器学习中真实数据的基本IID假设。然而，尽管源样本{z}服从IID分布，生成的{G(z)}未必是来自目标分布的IID采样。基于此观察，考虑IID生成的一个必要条件——来自目标数据的逆样本在源分布中也应服从IID，我们提出一种新损失函数，通过迫使潜空间中真实数据的逆样本与高斯源分布接近，从而正则化生成过程使其服从目标分布的IID性质。在合成数据和真实世界数据上的实验均验证了本模型的有效性。