Work

MLPro 2.0 - Online machine learning in Python

Year: 2025

Type: article

Abstract: In this paper, we present version 2.0 of the open-source middleware MLPro for applied machine learning in Python. Notably, it introduces the new sub-framework MLPro-OA for online machine learning, focusing on standards and templates for classic and online-adaptive data stream processing (DSP/OADSP). As part of this, we provide two novel adaptation mechanisms called cascaded and reverse adaptation. The first enables event-oriented cross-stream-task adaptation, decoupled from the forward-facing DSP. The second allows stream tasks to remove obsolete stream instances from their policies that were discarded from a previous sliding window. Furthermore, we provide insights into the underlying design criteria of MLPro-OA, which were developed through extensive requirements engineering. In the practical part of this work, we demonstrate the essential functionalities of MLPro-OA using reproducible examples.

Source: Machine Learning with Applications

DOI: 10.1016/j.mlwa.2025.100715

Authors: Detlef Arend, Laxmikant Shrikant Baheti, Steve Yuwono, Syamraj Purushamparambil Satheesh Kumar, Andreas Schwung

Institution: South Westphalia University of Applied Sciences

Language: English

Topic: Data Stream Mining Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,340

Funder: Fachhochschule Südwestfalen