Semantic Preserving Generative Adversarial Models
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.
Joint work with Shahar Harel and Meir Maor
Amir Ronen is the Chief Scientist of Spark Beyond. His main interests lie on the border of machine learning and algorithms. He is often fascinated by deep mathematical ideas that have far reaching practical implications. Amir did his Ph.D. at the Hebrew University under the supervision of Noam Nisan. He was a postdoctoral research fellow at Stanford University and UC Berkeley, a faculty member at the Technion, and a researcher at IBM. Amir received various awards including the Gödel prize, the Best Paper Prize from the International Joint Conferences Artificial Intelligence (IJCAI) and the Journal of Artificial Intelligence Research (JAIR), and the Wolf prize for Ph.D. Students.