Feature Selection as a Multiagent Coordination Problem

TL;DR

This paper introduces a novel multiagent reinforcement learning approach for feature selection in high-dimensional datasets, demonstrating improved scalability and performance over existing methods, especially in microarray gene expression data.

Contribution

The paper formulates feature selection as a multiagent coordination problem and proposes a scalable MARL method with CLEAN rewards, outperforming existing approaches.

Findings

MARL with CLEAN rewards scales well to thousands of features

Proposed method outperforms nine existing feature selection methods

Hybrid MARL variant achieves the best overall performance

Abstract

Datasets with hundreds to tens of thousands features is the new norm. Feature selection constitutes a central problem in machine learning, where the aim is to derive a representative set of features from which to construct a classification (or prediction) model for a specific task. Our experimental study involves microarray gene expression datasets, these are high-dimensional and noisy datasets that contain genetic data typically used for distinguishing between benign or malicious tissues or classifying different types of cancer. In this paper, we formulate feature selection as a multiagent coordination problem and propose a novel feature selection method using multiagent reinforcement learning. The central idea of the proposed approach is to "assign" a reinforcement learning agent to each feature where each agent learns to control a single feature, we refer to this approach as MARL. Applying this to microarray datasets creates an enormous multiagent coordination problem between thousands of learning agents. To address the scalability challenge we apply a form of reward shaping called CLEAN rewards. We compare in total nine feature selection methods, including state-of-the-art methods, and show that the proposed method using CLEAN rewards can significantly scale-up, thus outperforming the rest of learning-based methods. We further show that a hybrid variant of MARL achieves the best overall performance.