`

Timezone: »

 
Poster
Incorporating Interpretable Output Constraints in Bayesian Neural Networks
Wanqian Yang · Lars Lorch · Moritz Graule · Himabindu Lakkaraju · Finale Doshi-Velez

Thu Dec 10 09:00 PM -- 11:00 PM (PST) @ Poster Session 6 #1795
in Poster Session 7 »

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.

[ Paper ]

Author Information

Wanqian Yang (Harvard University)
Lars Lorch (Harvard)
Moritz Graule (Harvard University)
Himabindu Lakkaraju (Harvard)

Hima Lakkaraju is an Assistant Professor at Harvard University focusing on explainability, fairness, and robustness of machine learning models. She has also been working with various domain experts in criminal justice and healthcare to understand the real world implications of explainable and fair ML. Hima has recently been named one of the 35 innovators under 35 by MIT Tech Review, and has received best paper awards at SIAM International Conference on Data Mining (SDM) and INFORMS. She has given invited workshop talks at ICML, NeurIPS, AAAI, and CVPR, and her research has also been covered by various popular media outlets including the New York Times, MIT Tech Review, TIME, and Forbes. For more information, please visit: https://himalakkaraju.github.io/

Finale Doshi-Velez (Harvard)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors