Incorporating Interpretable Output Constraints in Bayesian Neural Networks [article]

Wanqian Yang, Lars Lorch, Moritz A. Graule, Himabindu Lakkaraju, Finale Doshi-Velez
2021 arXiv   pre-print
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
more » ... th 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.
arXiv:2010.10969v2 fatcat:ef4swnzfcjd2nkvmrajyklt5cq