Semantic Preserving Generative Adversarial Models
This work addresses the challenge of ensuring semantic fidelity in generative models for applications such as chemistry and telecommunications, representing a novel method rather than an incremental improvement.
The authors tackled the problem of generating data with guaranteed semantic properties by introducing generative adversarial models that use a calibrated classifier as the discriminator, resulting in models that require less data, provide natural stopping conditions, and generate objects with strong guarantees across domains like cellular antenna placement and molecule generation.
We introduce generative adversarial models in which the discriminator is replaced by a calibrated (non-differentiable) classifier repeatedly enhanced by domain relevant features. The role of the classifier is to prove that the actual and generated data differ over a controlled semantic space. We demonstrate that such models have the ability to generate objects with strong guarantees on their properties in a wide range of domains. They require less data than ordinary GANs, provide natural stopping conditions, uncover important properties of the data, and enhance transfer learning. Our techniques can be combined with standard generative models. We demonstrate the usefulness of our approach by applying it to several unrelated domains: generating good locations for cellular antennae, molecule generation preserving key chemical properties, and generating and extrapolating lines from very few data points. Intriguing open problems are presented as well.