Regularizing Black-box Models for Improved Interpretability
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, whose explanation quality can be unpredictable. Our method, ExpO, is a hybridization of these approaches that regularizes a model for explanation quality at training time. Importantly, these regularizers are differentiable, model agnostic, and require no domain knowledge to define. We demonstrate that post-hoc explanations for ExpO-regularized models have better explanation quality, as measured by the common fidelity and stability metrics. We verify that improving these metrics leads to significantly more useful explanations with a user study on a realistic task.
Code (1)
Tasks
BIG-bench Machine LearningInterpretable Machine LearningSimilar Papers 제목 키워드 기반
Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)
Most of the work on interpretable machine learning has focused on designing either inherently interpretable models, which typically trade-off accuracy for interpretability, or post-hoc explanation systems, which lack gua…
BIG-bench Machine LearningInterpretable Machine LearningExplaining Black-box Models for Biomedical Text Classification
In this paper, we propose a novel method named Biomedical Confident Itemsets Explanation (BioCIE), aiming at post-hoc explanation of black-box machine learning models for biomedical text classification. Using sources of …
ClassificationGeneral Classificationtext-classificationText ClassificationCausalSent: Interpretable Sentiment Classification with RieszNet
Despite the overwhelming performance improvements offered by recent natural language processing (NLP) models, the decisions made by these models are largely a black box. Towards closing this gap, the field of causal NLP …
Causal InferenceAchieving Constraints in Neural Networks: A Stochastic Augmented Lagrangian Approach
Regularizing Deep Neural Networks (DNNs) is essential for improving generalizability and preventing overfitting. Fixed penalty methods, though common, lack adaptability and suffer from hyperparameter sensitivity. In this…
VAE-LIME: Deep Generative Model Based Approach for Local Data-Driven Model Interpretability Applied to the Ironmaking Industry
Machine learning applied to generate data-driven models are lacking of transparency leading the process engineer to lose confidence in relying on the model predictions to optimize his industrial process. Bringing process…
modelTime Series Analysis