DeepAI AI Chat
Log In Sign Up

Selective Ensembles for Consistent Predictions

by   Emily Black, et al.

Recent work has shown that models trained to the same objective, and which achieve similar measures of accuracy on consistent test data, may nonetheless behave very differently on individual predictions. This inconsistency is undesirable in high-stakes contexts, such as medical diagnosis and finance. We show that this inconsistent behavior extends beyond predictions to feature attributions, which may likewise have negative implications for the intelligibility of a model, and one's ability to find recourse for subjects. We then introduce selective ensembles to mitigate such inconsistencies by applying hypothesis testing to the predictions of a set of models trained using randomly-selected starting conditions; importantly, selective ensembles can abstain in cases where a consistent outcome cannot be achieved up to a specified confidence level. We prove that that prediction disagreement between selective ensembles is bounded, and empirically demonstrate that selective ensembles achieve consistent predictions and feature attributions while maintaining low abstention rates. On several benchmark datasets, selective ensembles reach zero inconsistently predicted points, with abstention rates as low 1.5


page 1

page 2

page 3

page 4


ASPEST: Bridging the Gap Between Active Learning and Selective Prediction

Selective prediction aims to learn a reliable model that abstains from m...

Towards Consistent Predictive Confidence through Fitted Ensembles

Deep neural networks are behind many of the recent successes in machine ...

Unsupervised Selective Rationalization with Noise Injection

A major issue with using deep learning models in sensitive applications ...

Towards Class-Specific Unit

Class selectivity is an attribute of a unit in deep neural networks, whi...

LSCP: Locally Selective Combination in Parallel Outlier Ensembles

In unsupervised outlier ensembles, the absence of ground truth makes the...

Detecting Extrapolation with Local Ensembles

We present local ensembles, a method for detecting extrapolation at test...

Selective Classification Can Magnify Disparities Across Groups

Selective classification, in which models are allowed to abstain on unce...