# A knowledge-driven AutoML architecture

arXiv: https://arxiv.org/abs/2311.17124 · HTML: https://mlsanity.com/paper/2311.17124/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 45 references that are in the map.
- First posted on arXiv 28 Nov 2023.

## Builds on (most cited first, 24 of 24)

- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [AutoML: A Survey of the State-of-the-Art](https://mlsanity.com/paper/1908.00709/) (2019)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Meta-Learning: A Survey](https://mlsanity.com/paper/1810.03548/) (2018)
- [Explainable Machine Learning for Scientific Insights and Discoveries](https://mlsanity.com/paper/1905.08883/) (2019)
- [Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution](https://mlsanity.com/paper/1804.09081/) (2018)
- [Demystifying the Draft EU Artificial Intelligence Act](https://mlsanity.com/paper/2107.03721/) (2021)
- [AutoML to Date and Beyond: Challenges and Opportunities](https://mlsanity.com/paper/2010.10777/) (2020)
- [Automated Machine Learning: From Principles to Practices](https://mlsanity.com/paper/1810.13306/) (2018)
- [An ADMM Based Framework for AutoML Pipeline Configuration](https://mlsanity.com/paper/1905.00424/) (2019)
- [Trust in AutoML: Exploring Information Needs for Establishing Trust in Automated Machine Learning Systems](https://mlsanity.com/paper/2001.06509/) (2020)
- [One button machine for automating feature engineering in relational databases](https://mlsanity.com/paper/1706.00327/) (2017)
- [Automated Machine Learning: State-of-The-Art and Open Challenges](https://mlsanity.com/paper/1906.02287/) (2019)
- [Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Tools](https://mlsanity.com/paper/1908.05557/) (2019)
- [Amazon SageMaker Autopilot: a white box AutoML solution at scale](https://mlsanity.com/paper/2012.08483/) (2020)
- [PyGlove: Symbolic Programming for Automated Machine Learning](https://mlsanity.com/paper/2101.08809/) (2021)
- [Automated Evolutionary Approach for the Design of Composite Machine Learning Pipelines](https://mlsanity.com/paper/2106.15397/) (2021)
- [MLJ: A Julia package for composable machine learning](https://mlsanity.com/paper/2007.12285/) (2020)
- [Multi-Objective Automatic Machine Learning with AutoxgboostMC](https://mlsanity.com/paper/1908.10796/) (2019)
- [Knowledge Representation in Bicategories of Relations](https://mlsanity.com/paper/1706.00526/) (2017)
- [Evolution of Scikit-Learn Pipelines with Dynamic Structured Grammatical Evolution](https://mlsanity.com/paper/2004.00307/) (2020)
- [Teaching machines to understand data science code by semantic enrichment of dataflow graphs](https://mlsanity.com/paper/1807.05691/) (2018)
- [Efficient AutoML Pipeline Search with Matrix and Tensor Factorization](https://mlsanity.com/paper/2006.04216/) (2020)
- [Flexible model composition in machine learning and its implementation in MLJ](https://mlsanity.com/paper/2012.15505/) (2020)

## Abstract (arXiv)

This paper proposes a knowledge-driven AutoML architecture for pipeline and deep feature synthesis. The main goal is to render the AutoML process explainable and to leverage domain knowledge in the synthesis of pipelines and features. The architecture explores several novel ideas: first, the construction of pipelines and deep features is approached in an unified way. Next, synthesis is driven by a shared knowledge system, interactively queried as to what pipeline operations to use or features to compute. Lastly, the synthesis processes takes decisions at runtime using partial solutions and results of their application on data. Two experiments are conducted to demonstrate the functionality of a na"ive implementation of the proposed architecture and to discuss its advantages, trade-offs as well as future potential for AutoML.