Detecting Concept Drift in Neural Networks Using Chi-squared Goodness of Fit Testing

TL;DR

This paper proposes using the chi-squared goodness of fit test as a meta-algorithm to detect concept drift in neural networks, ensuring model reliability during inference without examining outputs directly.

Contribution

It introduces a novel application of the chi-squared test for concept drift detection across various neural network architectures in different inference scenarios.

Findings

Effective detection of accuracy drops due to drift

Applicable to multiple neural network architectures

Enhances model safety during deployment

Abstract

As the adoption of deep learning models has grown beyond human capacity for verification, meta-algorithms are needed to ensure reliable model inference. Concept drift detection is a field dedicated to identifying statistical shifts that is underutilized in monitoring neural networks that may encounter inference data with distributional characteristics diverging from their training data. Given the wide variety of model architectures, applications, and datasets, it is important that concept drift detection algorithms are adaptable to different inference scenarios. In this paper, we introduce an application of the $\chi^2$ Goodness of Fit Hypothesis Test as a drift detection meta-algorithm applied to a multilayer perceptron, a convolutional neural network, and a transformer trained for machine vision as they are exposed to simulated drift during inference. To that end, we demonstrate how unexpected drops in accuracy due to concept drift can be detected without directly examining the inference outputs. Our approach enhances safety by ensuring models are continually evaluated for reliability across varying conditions.