论文标题
在贝叶斯神经网络中纳入可解释的产出约束
Incorporating Interpretable Output Constraints in Bayesian Neural Networks
论文作者
论文摘要
部署监督模型的域通常会带有特定于任务的约束，例如先前的有关地面真相功能的专家知识，或者像安全性和公平性一样。我们引入了一个新颖的概率框架，用于通过这种约束来推理并提出先验，使我们能够有效地将它们纳入贝叶斯神经网络（BNN），包括可以在任务上摊销的变体。所得的输出约束的BNN（OC-BNN）与贝叶斯框架的不确定性定量完全一致，并且可以与黑盒推理相提并论。与典型的BNN推断在无法解释的参数空间中，OC-BNN扩大了可以合并的功能知识范围，尤其是对于没有机器学习专业知识的模型用户而言。我们证明了OC-BNN在现实世界数据集上的功效，涵盖了医疗保健，刑事司法和信用评分等多个领域。
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.
