Publications
Publications
- Advances in Neural Information Processing Systems (NeurIPS)
Incorporating Interpretable Output Constraints in Bayesian Neural Networks
By: Wanqian Yang, Lars Lorch, Moritz Graule, Himabindu Lakkaraju and Finale Doshi-Velez
Abstract
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.
Citation
Yang, Wanqian, Lars Lorch, Moritz Graule, Himabindu Lakkaraju, and Finale Doshi-Velez. "Incorporating Interpretable Output Constraints in Bayesian Neural Networks." Advances in Neural Information Processing Systems (NeurIPS) 33 (2020).