Identifying Unknown Unknowns in the Open World: Representations and Policies for Guided Exploration

by   Himabindu Lakkaraju, et al.

Predictive models deployed in the real world may assign incorrect labels to instances with high confidence. Such errors or unknown unknowns are rooted in model incompleteness, and typically arise because of the mismatch between training data and the cases encountered at test time. As the models are blind to such errors, input from an oracle is needed to identify these failures. In this paper, we formulate and address the problem of informed discovery of unknown unknowns of any given predictive model where unknown unknowns occur due to systematic biases in the training data. We propose a model-agnostic methodology which uses feedback from an oracle to both identify unknown unknowns and to intelligently guide the discovery. We employ a two-phase approach which first organizes the data into multiple partitions based on the feature similarity of instances and the confidence scores assigned by the predictive model, and then utilizes an explore-exploit strategy for discovering unknown unknowns across these partitions. We demonstrate the efficacy of our framework by varying the underlying causes of unknown unknowns across various applications. To the best of our knowledge, this paper presents the first algorithmic approach to the problem of discovering unknown unknowns of predictive models.


page 1

page 2

page 3

page 4


Discovering Blind Spots in Reinforcement Learning

Agents trained in simulation may make errors in the real world due to mi...

Facility Locations Utility for Uncovering Classifier Overconfidence

Assessing the predictive accuracy of black box classifiers is challengin...

Achieving Representative Data via Convex Hull Feasibility Sampling Algorithms

Sampling biases in training data are a major source of algorithmic biase...

Discovering Markov Blanket from Multiple interventional Datasets

In this paper, we study the problem of discovering the Markov blanket (M...

Towards Open World Object Detection

Humans have a natural instinct to identify unknown object instances in t...

Discovering Human-Object Interaction Concepts via Self-Compositional Learning

A comprehensive understanding of human-object interaction (HOI) requires...

Repairing Neural Networks by Leaving the Right Past Behind

Prediction failures of machine learning models often arise from deficien...

Please sign up or login with your details

Forgot password? Click here to reset