Classification with Costly Features using Deep Reinforcement Learning

TL;DR

This paper enhances cost-sensitive classification by applying deep reinforcement learning with neural networks, improving robustness and flexibility over previous linear approximation methods across multiple datasets.

Contribution

It replaces linear approximation with neural networks in a reinforcement learning framework for costly feature classification, achieving comparable or better results.

Findings

Neural network-based approach matches state-of-the-art performance.

The method is flexible and can incorporate improvements and pre-trained classifiers.

Robust performance across all tested datasets.

Abstract

We study a classification problem where each feature can be acquired for a cost and the goal is to optimize a trade-off between the expected classification error and the feature cost. We revisit a former approach that has framed the problem as a sequential decision-making problem and solved it by Q-learning with a linear approximation, where individual actions are either requests for feature values or terminate the episode by providing a classification decision. On a set of eight problems, we demonstrate that by replacing the linear approximation with neural networks the approach becomes comparable to the state-of-the-art algorithms developed specifically for this problem. The approach is flexible, as it can be improved with any new reinforcement learning enhancement, it allows inclusion of pre-trained high-performance classifier, and unlike prior art, its performance is robust across all evaluated datasets.