Interpreting Shared Deep Learning Models via Explicable Boundary Trees

By Huijun Wu, Chen Wang, Jie Yin, Kai Lu, Liming Zhu. 2017

6 citations recorded by the source corpus.

Despite outperforming the human in many tasks, deep neural network models are also criticized for the lack of transparency and interpretability in decision making. The opaqueness results in uncertainty and low confidence when deploying such a model in model sharing scenarios, when the model is developed by a third party. For a supervised machine learning model, sharing training process including training data provides an effective way to gain trust and to better understand model predictions. However, it is not always possible to share all training data due to privacy and policy constraints. In this paper, we propose a method to disclose a small set of training data that is just sufficient for users to get the insight of a complicated model. The method constructs a boundary tree using selected training data and the tree is able to approximate the complicated model with high fidelity. We show that traversing data points in the tree gives users significantly better understanding of the model and paves the way for trustworthy model sharing.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Conservative Q-Improvement: Reinforcement Learning for an Interpretable Decision-Tree Policy (2019, background): “It is difﬁ-cult for humans to trust decisions that cannot be veriﬁed, and thus much research has gone into creating interpretable models [Wu et al. , 2017] as part of general growing interest in interpretable AI [Bloomberg, 2018].”