Counterexample-Guided Learning of Monotonic Neural Networks

Abstract

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.

References in corpus (11)

• Adam: A Method for Stochastic Optimization
• End to End Learning for Self-Driving Cars
• Equality of Opportunity in Supervised Learning
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Towards Deep Neural Network Architectures Robust to Adversarial Examples
• Certified Defenses against Adversarial Examples
• Certifying Some Distributional Robustness with Principled Adversarial Training
• Input Convex Neural Networks
• Reachable Set Computation and Safety Verification for Neural Networks with ReLU Activations
• Learning from Sparse Data by Exploiting Monotonicity Constraints
• How to Incorporate Monotonicity in Deep Networks While Preserving Flexibility?