Counterexample-Guided Learning of Monotonic Neural Networks
This addresses the need for domain-specific constraints like monotonicity in deep learning models for real-world applications, offering a novel enforcement method without restricting the hypothesis space.
The paper tackles the problem of enforcing monotonicity constraints in neural networks, developing a counterexample-guided technique that provably ensures monotonicity at prediction time and uses it as an inductive bias during training, achieving state-of-the-art results on real-world datasets.
The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias. However, in many real-world tasks, the learned function is intended to satisfy domain-specific constraints. We focus on monotonicity constraints, which are common and require that the function's output increases with increasing values of specific input features. We develop a counterexample-guided technique to provably enforce monotonicity constraints at prediction time. Additionally, we propose a technique to use monotonicity as an inductive bias for deep learning. It works by iteratively incorporating monotonicity counterexamples in the learning process. Contrary to prior work in monotonic learning, we target general ReLU neural networks and do not further restrict the hypothesis space. We have implemented these techniques in a tool called COMET. Experiments on real-world datasets demonstrate that our approach achieves state-of-the-art results compared to existing monotonic learners, and can improve the model quality compared to those that were trained without taking monotonicity constraints into account.