A Chance-Constrained Generative Framework for Sequence Optimization

Deep generative modeling has achieved many successes for continuous data generation, such as producing realistic images and controlling their properties (e. g. , styles). However, the development of generative modeling techniques for optimizing discrete data, such as sequences or strings, still lags behind largely due to the challenges in modeling complex and long-range constraints, including both syntax and semantics, in discrete structures. In this paper, we formulate the sequence optimization task as a chance-constrained optimization problem. The key idea is to enforce a high probability of generating valid sequences and also optimize the property of interest. We propose a novel minimax algorithm to simultaneously tighten a bound of the valid chance and optimize the expected property. Extensive experimental results in three domains demonstrate the superiority of our approach over the existing sequence optimization methods.

Authors

• Xianggen Liu
• Qiang Liu 0001
• Sen Song
• Jian Peng 0001

Keywords

No keywords are indexed for this paper.