Into the Unknown: Active Monitoring of Neural Networks

TL;DR

This paper presents an active monitoring framework for neural networks that interactively detects and adapts to novel input classes in dynamic environments, improving accuracy through human-in-the-loop updates.

Contribution

It introduces a novel framework combining a parallel monitor and adaptive detection to handle unknown classes, with interactive human feedback for continual learning.

Findings

Enhanced detection of novel classes in dynamic scenarios

Improved accuracy through adaptive monitoring

Effective in diverse benchmark environments

Abstract

Neural-network classifiers achieve high accuracy when predicting the class of an input that they were trained to identify. Maintaining this accuracy in dynamic environments, where inputs frequently fall outside the fixed set of initially known classes, remains a challenge. The typical approach is to detect inputs from novel classes and retrain the classifier on an augmented dataset. However, not only the classifier but also the detection mechanism needs to adapt in order to distinguish between newly learned and yet unknown input classes. To address this challenge, we introduce an algorithmic framework for active monitoring of a neural network. A monitor wrapped in our framework operates in parallel with the neural network and interacts with a human user via a series of interpretable labeling queries for incremental adaptation. In addition, we propose an adaptive quantitative monitor to improve precision. An experimental evaluation on a diverse set of benchmarks with varying numbers of classes confirms the benefits of our active monitoring framework in dynamic scenarios.