论文标题
基于MIM的GAN：信息指标，以扩大生成对抗网络中的小概率事件的重要性
MIM-Based GAN: Information Metric to Amplify Small Probability Events Importance in Generative Adversarial Networks
论文作者
论文摘要
就生成对抗网络（GAN）而言，将生成数据与真实数据区分开的信息指标在于发电效率的关键点，在基于GAN的应用程序中起着重要作用，尤其是在异常检测中。至于原始的gan，基于KL差异的差异，存在其隐藏信息度量的缺点，这些差异是对对抗性网络的罕见事件生成和培训性能的缺点。因此，研究用于提高发电能力并带来训练过程中的增益的甘恩斯所使用的指标很重要。在本文中，我们采用了从信息度量（即MIM）提及的指数形式来替换原始gan的对数形式。这种方法称为基于MIM的GAN，在网络培训和罕见事件的一生中具有更好的性能。具体来说，我们首先在这种方法中讨论培训过程的特征。此外，我们还分析了其在理论上产生罕见事件的优势。此外，我们在MNIST的数据集上进行了模拟，并且与某些经典gan相比，基于MIM的GAN在异常检测方面实现了最先进的性能。
In terms of Generative Adversarial Networks (GANs), the information metric to discriminate the generative data from the real data, lies in the key point of generation efficiency, which plays an important role in GAN-based applications, especially in anomaly detection. As for the original GAN, there exist drawbacks for its hidden information measure based on KL divergence on rare events generation and training performance for adversarial networks. Therefore, it is significant to investigate the metrics used in GANs to improve the generation ability as well as bring gains in the training process. In this paper, we adopt the exponential form, referred from the information measure, i.e. MIM, to replace the logarithm form of the original GAN. This approach is called MIM-based GAN, has better performance on networks training and rare events generation. Specifically, we first discuss the characteristics of training process in this approach. Moreover, we also analyze its advantages on generating rare events in theory. In addition, we do simulations on the datasets of MNIST and ODDS to see that the MIM-based GAN achieves state-of-the-art performance on anomaly detection compared with some classical GANs.
