Uncertainty quantification and out-of-distribution detection using surjective normalizing flows

TL;DR

This paper introduces a surjective normalizing flow method for efficient out-of-distribution detection and uncertainty quantification in deep neural networks, demonstrating its effectiveness on synthetic mobility data.

Contribution

The paper presents a novel surjective normalizing flow approach for OOD detection that outperforms existing models like Dirichlet process mixtures and bijective flows.

Findings

Surjective flows reliably distinguish in- and out-of-distribution data.

The method performs well on synthetic mobility datasets.

Surjections are key to effective OOD detection.

Abstract

Reliable quantification of epistemic and aleatoric uncertainty is of crucial importance in applications where models are trained in one environment but applied to multiple different environments, often seen in real-world applications for example, in climate science or mobility analysis. We propose a simple approach using surjective normalizing flows to identify out-of-distribution data sets in deep neural network models that can be computed in a single forward pass. The method builds on recent developments in deep uncertainty quantification and generative modeling with normalizing flows. We apply our method to a synthetic data set that has been simulated using a mechanistic model from the mobility literature and several data sets simulated from interventional distributions induced by soft and atomic interventions on that model, and demonstrate that our method can reliably discern out-of-distribution data from in-distribution data. We compare the surjective flow model to a Dirichlet process mixture model and a bijective flow and find that the surjections are a crucial component to reliably distinguish in-distribution from out-of-distribution data.