# IIFE: Interaction Information Based Automated Feature Engineering

arXiv: https://arxiv.org/abs/2409.04665 · HTML: https://mlsanity.com/paper/2409.04665/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 33 references that are in the map.
- First posted on arXiv 7 Sep 2024.

## Builds on (most cited first, 8 of 8)

- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Accounting for Variance in Machine Learning Benchmarks](https://mlsanity.com/paper/2103.03098/) (2021)
- [Feature Engineering for Predictive Modeling using Reinforcement Learning](https://mlsanity.com/paper/1709.07150/) (2017)
- [The autofeat Python Library for Automated Feature Engineering and Selection](https://mlsanity.com/paper/1901.07329/) (2019)
- [OpenFE: Automated Feature Generation with Expert-level Performance](https://mlsanity.com/paper/2211.12507/) (2022)
- [DIFER: Differentiable Automated Feature Engineering](https://mlsanity.com/paper/2010.08784/) (2020)
- [Endgame Analysis of Dou Shou Qi](https://mlsanity.com/paper/1604.07312/) (2016)
- [Conditional Mutual Information Estimation for Mixed Discrete and Continuous Variables with Nearest Neighbors](https://mlsanity.com/paper/1912.03387/) (2019)

## Built on by (most cited first, 4 of 4)

- [Tabular Feature Discovery With Reasoning Type Exploration](https://mlsanity.com/paper/2506.20357/) (2025)
- [Federated Automated Feature Engineering](https://mlsanity.com/paper/2412.04404/) (2024)
- [Enhancing Dimensionality Prediction in Hybrid Metal Halides via Feature Engineering and Class-Imbalance Mitigation](https://mlsanity.com/paper/2512.05367/) (2025)
- [SCOPE-FE: Structured Control of Operator and Pairwise Exploration for Feature Engineering via Quality-Aware Candidate-Space Reduction](https://mlsanity.com/paper/2604.27025/) (2026)

## Abstract (arXiv)

Automated feature engineering (AutoFE) is the process of automatically building and selecting new features that help improve downstream predictive performance. While traditional feature engineering requires significant domain expertise and time-consuming iterative testing, AutoFE strives to make feature engineering easy and accessible to all data science practitioners. We introduce a new AutoFE algorithm, IIFE, based on determining which feature pairs synergize well through an information-theoretic perspective called interaction information. We demonstrate the superior performance of IIFE over existing algorithms. We also show how interaction information can be used to improve existing AutoFE algorithms. Finally, we highlight several critical experimental setup issues in the existing AutoFE literature and their effects on performance.