On Positive-Unlabeled Classification in GAN
This addresses training instability in GANs for generative modeling, but it is incremental as it builds on standard GAN frameworks.
The paper tackles the instability of GAN training by redefining the discriminator's classification problem as positive-unlabeled instead of positive-negative, leading to a new model called PUGAN that achieves comparable or better performance than existing stabilization methods.
This paper defines a positive and unlabeled classification problem for standard GANs, which then leads to a novel technique to stabilize the training of the discriminator in GANs. Traditionally, real data are taken as positive while generated data are negative. This positive-negative classification criterion was kept fixed all through the learning process of the discriminator without considering the gradually improved quality of generated data, even if they could be more realistic than real data at times. In contrast, it is more reasonable to treat the generated data as unlabeled, which could be positive or negative according to their quality. The discriminator is thus a classifier for this positive and unlabeled classification problem, and we derive a new Positive-Unlabeled GAN (PUGAN). We theoretically discuss the global optimality the proposed model will achieve and the equivalent optimization goal. Empirically, we find that PUGAN can achieve comparable or even better performance than those sophisticated discriminator stabilization methods.