An incremental linear-time learning algorithm for the Optimum-Path Forest classifier

TL;DR

This paper introduces an incremental linear-time learning algorithm for the Optimum-Path Forest classifier, enabling faster updates with maintained accuracy for large datasets.

Contribution

The paper presents a novel incremental learning algorithm for OPF that reduces training time from quadratic to linear complexity.

Findings

Inclusion of new instances in linear time without significant accuracy loss

Comparable accuracy to the original quadratic-time OPF model

Enhanced scalability for large datasets

Abstract

We present a classification method with incremental capabilities based on the Optimum-Path Forest classifier (OPF). The OPF considers instances as nodes of a fully-connected training graph, arc weights represent distances between two feature vectors. Our algorithm includes new instances in an OPF in linear-time, while keeping similar accuracies when compared with the original quadratic-time model.