# Evolving machine learning workflows through interactive AutoML

arXiv: https://arxiv.org/abs/2402.18505 · HTML: https://mlsanity.com/paper/2402.18505/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 43 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 12 of 12)

- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice](https://mlsanity.com/paper/2007.15745/) (2020)
- [Evaluation of a Tree-based Pipeline Optimization Tool for Automating Data Science](https://mlsanity.com/paper/1603.06212/) (2016)
- [AutoDS: Towards Human-Centered Automation of Data Science](https://mlsanity.com/paper/2101.05273/) (2021)
- [PipelineProfiler: A Visual Analytics Tool for the Exploration of AutoML Pipelines](https://mlsanity.com/paper/2005.00160/) (2020)
- [AutoML in The Wild: Obstacles, Workarounds, and Expectations](https://mlsanity.com/paper/2302.10827/) (2023)
- [Layered TPOT: Speeding up Tree-based Pipeline Optimization](https://mlsanity.com/paper/1801.06007/) (2018)
- [HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks](https://mlsanity.com/paper/2009.02078/) (2020)
- [Evolution of Scikit-Learn Pipelines with Dynamic Structured Grammatical Evolution](https://mlsanity.com/paper/2004.00307/) (2020)
- [Interpretable Automated Machine Learning in Maana(TM) Knowledge Platform](https://mlsanity.com/paper/1905.02168/) (2019)
- [Interactive Multi-Objective Evolutionary Optimization of Software Architectures](https://mlsanity.com/paper/2401.04192/) (2024)
- [A Multi-Objective Anytime Rule Mining System to Ease Iterative Feedback from Domain Experts](https://mlsanity.com/paper/1812.09746/) (2018)

## Built on by (most cited first, 1 of 1)

- [Large Language Model-Empowered Interactive Load Forecasting](https://mlsanity.com/paper/2505.16577/) (2025)

## Abstract (arXiv)

Automatic workflow composition (AWC) is a relevant problem in automated machine learning (AutoML) that allows finding suitable sequences of preprocessing and prediction models together with their optimal hyperparameters. This problem can be solved using evolutionary algorithms and, in particular, grammar-guided genetic programming (G3P). Current G3P approaches to AWC define a fixed grammar that formally specifies how workflow elements can be combined and which algorithms can be included. In this paper we present ourmethod, an interactive G3P algorithm that allows users to dynamically modify the grammar to prune the search space and focus on their regions of interest. Our proposal is the first to combine the advantages of a G3P method with ideas from interactive optimisation and human-guided machine learning, an area little explored in the context of AutoML. To evaluate our approach, we present an experimental study in which 20 participants interact with ourmethod to evolve workflows according to their preferences. Our results confirm that the collaboration between ourmethod and humans allows us to find high-performance workflows in terms of accuracy that require less tuning time than those found without human intervention.