Incorporating Interpretable Output Constraints in Bayesian Neural Networks

10/21/2020
by   Wanqian Yang, et al.
0

Domains where supervised models are deployed often come with task-specific constraints, such as prior expert knowledge on the ground-truth function, or desiderata like safety and fairness. We introduce a novel probabilistic framework for reasoning with such constraints and formulate a prior that enables us to effectively incorporate them into Bayesian neural networks (BNNs), including a variant that can be amortized over tasks. The resulting Output-Constrained BNN (OC-BNN) is fully consistent with the Bayesian framework for uncertainty quantification and is amenable to black-box inference. Unlike typical BNN inference in uninterpretable parameter space, OC-BNNs widen the range of functional knowledge that can be incorporated, especially for model users without expertise in machine learning. We demonstrate the efficacy of OC-BNNs on real-world datasets, spanning multiple domains such as healthcare, criminal justice, and credit scoring.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/15/2019

Output-Constrained Bayesian Neural Networks

Bayesian neural network (BNN) priors are defined in parameter space, mak...
research
03/18/2019

Combining Model and Parameter Uncertainty in Bayesian Neural Networks

Bayesian neural networks (BNNs) have recently regained a significant amo...
research
12/10/2017

Sensitivity Analysis for Predictive Uncertainty in Bayesian Neural Networks

We derive a novel sensitivity analysis of input variables for predictive...
research
10/16/2022

Posterior Regularized Bayesian Neural Network Incorporating Soft and Hard Knowledge Constraints

Neural Networks (NNs) have been widely used in supervised learning due t...
research
05/09/2023

Fully Bayesian VIB-DeepSSM

Statistical shape modeling (SSM) enables population-based quantitative a...
research
03/07/2022

Prior-informed Uncertainty Modelling with Bayesian Polynomial Approximations

Orthogonal polynomial approximations form the foundation to a set of wel...
research
04/29/2023

EBLIME: Enhanced Bayesian Local Interpretable Model-agnostic Explanations

We propose EBLIME to explain black-box machine learning models and obtai...

Please sign up or login with your details

Forgot password? Click here to reset