Log In Sign Up

Certified Monotonic Neural Networks

by   Xingchao Liu, et al.

Learning monotonic models with respect to a subset of the inputs is a desirable feature to effectively address the fairness, interpretability, and generalization issues in practice. Existing methods for learning monotonic neural networks either require specifically designed model structures to ensure monotonicity, which can be too restrictive/complicated, or enforce monotonicity by adjusting the learning process, which cannot provably guarantee the learned model is monotonic on selected features. In this work, we propose to certify the monotonicity of the general piece-wise linear neural networks by solving a mixed integer linear programming problem.This provides a new general approach for learning monotonic neural networks with arbitrary model structures. Our method allows us to train neural networks with heuristic monotonicity regularizations, and we can gradually increase the regularization magnitude until the learned network is certified monotonic. Compared to prior works, our approach does not require human-designed constraints on the weight space and also yields more accurate approximation. Empirical studies on various datasets demonstrate the efficiency of our approach over the state-of-the-art methods, such as Deep Lattice Networks.


Counterexample-Guided Learning of Monotonic Neural Networks

The widespread adoption of deep learning is often attributed to its auto...

Monotonic Trends in Deep Neural Networks

The importance of domain knowledge in enhancing model performance and ma...

Deep Lattice Networks and Partial Monotonic Functions

We propose learning deep models that are monotonic with respect to a use...

Unconstrained Monotonic Neural Networks

Monotonic neural networks have recently been proposed as a way to define...

Recalling a Witness: Foundations and Applications of Monotonic State

We provide a way to ease the verification of programs whose state evolve...

Individual Fairness Guarantees for Neural Networks

We consider the problem of certifying the individual fairness (IF) of fe...

Training Neural Networks for Solving 1-D Optimal Piecewise Linear Approximation

Recently, the interpretability of deep learning has attracted a lot of a...

Code Repositories