# Flexible model composition in machine learning and its implementation in MLJ

arXiv: https://arxiv.org/abs/2012.15505 · HTML: https://mlsanity.com/paper/2012.15505/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2020.

## Built on by (most cited first, 3 of 3)

- [ReservoirComputing.jl: An Efficient and Modular Library for Reservoir Computing Models](https://mlsanity.com/paper/2204.05117/) (2022)
- [OutlierDetection.jl: A modular outlier detection ecosystem for the Julia programming language](https://mlsanity.com/paper/2211.04550/) (2022)
- [A knowledge-driven AutoML architecture](https://mlsanity.com/paper/2311.17124/) (2023)

## Abstract (arXiv)

A graph-based protocol called `learning networks' which combine assorted machine learning models into meta-models is described. Learning networks are shown to overcome several limitations of model composition as implemented in the dominant machine learning platforms. After illustrating the protocol in simple examples, a concise syntax for specifying a learning network, implemented in the MLJ framework, is presented. Using the syntax, it is shown that learning networks are are sufficiently flexible to include Wolpert's model stacking, with out-of-sample predictions for the base learners.