Meet MASKS: A novel Multi-Classifier's verification approach

TL;DR

This paper introduces MASKS, a multi-agent ensemble classifier verification method that significantly reduces error rates by integrating multiple classifiers and verifying safety properties across datasets.

Contribution

The paper presents a novel multi-agent system and verification approach called MASKS, enhancing classifier ensemble accuracy through logical verification and knowledge sharing.

Findings

Reduced error rate to about one-tenth of individual classifiers

Effective verification of safety properties in classifier ensembles

Demonstrated success across multiple datasets

Abstract

In this study, a new ensemble approach for classifiers is introduced. A verification method for better error elimination is developed through the integration of multiple classifiers. A multi-agent system comprised of multiple classifiers is designed to verify the satisfaction of the safety property. In order to examine the reasoning concerning the aggregation of the distributed knowledge, a logical model has been proposed. To verify predefined properties, a Multi-Agent Systems' Knowledge-Sharing algorithm (MASKS) has been formulated and developed. As a rigorous evaluation, we applied this model to the Fashion-MNIST, MNIST, and Fruit-360 datasets, where it reduced the error rate to approximately one-tenth of the individual classifiers.