Interpretable & Explorable Approximations of Black Box Models

07/04/2017
by   Himabindu Lakkaraju, et al.
0

We propose Black Box Explanations through Transparent Approximations (BETA), a novel model agnostic framework for explaining the behavior of any black-box classifier by simultaneously optimizing for fidelity to the original model and interpretability of the explanation. To this end, we develop a novel objective function which allows us to learn (with optimality guarantees), a small number of compact decision sets each of which explains the behavior of the black box model in unambiguous, well-defined regions of feature space. Furthermore, our framework also is capable of accepting user input when generating these approximations, thus allowing users to interactively explore how the black-box model behaves in different subspaces that are of interest to the user. To the best of our knowledge, this is the first approach which can produce global explanations of the behavior of any given black box model through joint optimization of unambiguity, fidelity, and interpretability, while also allowing users to explore model behavior based on their preferences. Experimental evaluation with real-world datasets and user studies demonstrates that our approach can generate highly compact, easy-to-understand, yet accurate approximations of various kinds of predictive models compared to state-of-the-art baselines.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/15/2019

"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations

As machine learning black boxes are increasingly being deployed in criti...
research
09/15/2020

Interpretable and Interactive Summaries of Actionable Recourses

As predictive models are increasingly being deployed in high-stakes deci...
research
12/24/2020

Sentence-Based Model Agnostic NLP Interpretability

Today, interpretability of Black-Box Natural Language Processing (NLP) m...
research
04/01/2019

VINE: Visualizing Statistical Interactions in Black Box Models

As machine learning becomes more pervasive, there is an urgent need for ...
research
11/06/2022

ProtoX: Explaining a Reinforcement Learning Agent via Prototyping

While deep reinforcement learning has proven to be successful in solving...
research
05/04/2022

Explainable Knowledge Graph Embedding: Inference Reconciliation for Knowledge Inferences Supporting Robot Actions

Learned knowledge graph representations supporting robots contain a weal...
research
12/07/2018

Dice in the Black Box: User Experiences with an Inscrutable Algorithm

We demonstrate that users may be prone to place an inordinate amount of ...

Please sign up or login with your details

Forgot password? Click here to reset