Adversarial Constraint Learning for Structured Prediction

Adversarial Constraint Learning for Structured Prediction

Hongyu Ren, Russell Stewart, Jiaming Song, Volodymyr Kuleshov, Stefano Ermon

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence
Main track. Pages 2637-2643. https://doi.org/10.24963/ijcai.2018/366

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these constraints and using them for supervision, bypassing the difficulty of using domain expertise to manually specify constraints. Learning requires a black-box simulator of structured outputs, which generates valid labels, but need not model their corresponding inputs or the input-label relationship. At training time, we constrain the model to produce outputs that cannot be distinguished from simulated labels by adversarial training. Providing our framework with a small number of labeled inputs gives rise to a new semi-supervised structured prediction model; we evaluate this model on multiple tasks --- tracking, pose estimation and time series prediction --- and find that it achieves high accuracy with only a small number of labeled inputs. In some cases, no labels are required at all. 
Keywords:
Machine Learning: Semi-Supervised Learning
Machine Learning: Structured Prediction