How to solve a classification problem using a cooperative tiling Multi-Agent System?

TL;DR

This paper introduces a cooperative multi-agent system framework that transforms classification problems into cooperative tilings of input space, enabling linear classifiers to perform effectively on non-linear problems.

Contribution

It presents a novel ensemble-based AMAS framework that enhances linear classifiers' performance on non-linear classification tasks through cooperative tiling.

Findings

Linear classifiers achieve better accuracy on non-linear problems.

Cooperative tiling improves decision boundary flexibility.

Framework successfully applied to benchmark problems.

Abstract

Adaptive Multi-Agent Systems (AMAS) transform dynamic problems into problems of local cooperation between agents. We present smapy, an ensemble based AMAS implementation for mobility prediction, whose agents are provided with machine learning models in addition to their cooperation rules. With a detailed methodology, we propose a framework to transform a classification problem into a cooperative tiling of the input variable space. We show that it is possible to use linear classifiers for online non-linear classification on three benchmark toy problems chosen for their different levels of linear separability, if they are integrated in a cooperative Multi-Agent structure. The results obtained show a significant improvement of the performance of linear classifiers in non-linear contexts in terms of classification accuracy and decision boundaries, thanks to the cooperative approach.