# FastFT: Accelerating Reinforced Feature Transformation via Advanced Exploration Strategies

arXiv: https://arxiv.org/abs/2503.20394 · HTML: https://mlsanity.com/paper/2503.20394/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 59 references that are in the map.
- First posted on arXiv 26 Mar 2025.

## Builds on (most cited first, 30 of 34)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Deep Reinforcement Learning with Double Q-learning](https://mlsanity.com/paper/1509.06461/) (2015)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Dueling Network Architectures for Deep Reinforcement Learning](https://mlsanity.com/paper/1511.06581/) (2015)
- [Deep Neural Networks and Tabular Data: A Survey](https://mlsanity.com/paper/2110.01889/) (2021)
- [Randomized Prior Functions for Deep Reinforcement Learning](https://mlsanity.com/paper/1806.03335/) (2018)
- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [Recurrent Neural Network for Text Classification with Multi-Task Learning](https://mlsanity.com/paper/1605.05101/) (2016)
- [Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering](https://mlsanity.com/paper/2305.03403/) (2023)
- [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)
- [Anti-Exploration by Random Network Distillation](https://mlsanity.com/paper/2301.13616/) (2023)
- [AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications](https://mlsanity.com/paper/1904.12857/) (2019)
- [Group-wise Reinforcement Feature Generation for Optimal and Explainable Representation Space Reconstruction](https://mlsanity.com/paper/2205.14526/) (2022)
- [Exploration and Anti-Exploration with Distributional Random Network Distillation](https://mlsanity.com/paper/2401.09750/) (2024)
- [One button machine for automating feature engineering in relational databases](https://mlsanity.com/paper/1706.00327/) (2017)
- [AutoDS: Towards Human-Centered Automation of Data Science](https://mlsanity.com/paper/2101.05273/) (2021)
- [Self-optimizing Feature Generation via Categorical Hashing Representation and Hierarchical Reinforcement Crossing](https://mlsanity.com/paper/2309.04612/) (2023)
- [Beyond Discrete Selection: Continuous Embedding Space Optimization for Generative Feature Selection](https://mlsanity.com/paper/2302.13221/) (2023)
- [Dynamic and Adaptive Feature Generation with LLM](https://mlsanity.com/paper/2406.03505/) (2024)
- [Traceable Automatic Feature Transformation via Cascading Actor-Critic Agents](https://mlsanity.com/paper/2212.13402/) (2022)
- [Traceable Group-Wise Self-Optimizing Feature Transformation Learning: A Dual Optimization Perspective](https://mlsanity.com/paper/2306.16893/) (2023)
- [From Supervised to Generative: A Novel Paradigm for Tabular Deep Learning with Large Language Models](https://mlsanity.com/paper/2310.07338/) (2023)
- [Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions](https://mlsanity.com/paper/2309.13618/) (2023)
- [ChatGPT as your Personal Data Scientist](https://mlsanity.com/paper/2305.13657/) (2023)
- [Unsupervised Generative Feature Transformation via Graph Contrastive Pre-training and Multi-objective Fine-tuning](https://mlsanity.com/paper/2405.16879/) (2024)
- [Techniques for Automated Machine Learning](https://mlsanity.com/paper/1907.08908/) (2019)
- [DIFER: Differentiable Automated Feature Engineering](https://mlsanity.com/paper/2010.08784/) (2020)

## Built on by (most cited first, 5 of 5)

- [Autonomous Data Agents: A New Opportunity for Smart Data](https://mlsanity.com/paper/2509.18710/) (2025)
- [FAMOSE: A ReAct Approach to Automated Feature Discovery](https://mlsanity.com/paper/2602.17641/) (2026)
- [Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimization](https://mlsanity.com/paper/2504.17355/) (2025)
- [Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2504.17356/) (2025)
- [Knowledge-Driven Agentic Scientific Corpus Distillation Framework for Biomedical Large Language Models Training](https://mlsanity.com/paper/2504.19565/) (2025)

## Abstract (arXiv)

Feature Transformation is crucial for classic machine learning that aims to generate feature combinations to enhance the performance of downstream tasks from a data-centric perspective. Current methodologies, such as manual expert-driven processes, iterative-feedback techniques, and exploration-generative tactics, have shown promise in automating such data engineering workflow by minimizing human involvement. However, three challenges remain in those frameworks: (1) It predominantly depends on downstream task performance metrics, as assessment is time-consuming, especially for large datasets. (2) The diversity of feature combinations will hardly be guaranteed after random exploration ends. (3) Rare significant transformations lead to sparse valuable feedback that hinders the learning processes or leads to less effective results. In response to these challenges, we introduce FastFT, an innovative framework that leverages a trio of advanced strategies.We first decouple the feature transformation evaluation from the outcomes of the generated datasets via the performance predictor. To address the issue of reward sparsity, we developed a method to evaluate the novelty of generated transformation sequences. Incorporating this novelty into the reward function accelerates the model's exploration of effective transformations, thereby improving the search productivity. Additionally, we combine novelty and performance to create a prioritized memory buffer, ensuring that essential experiences are effectively revisited during exploration. Our extensive experimental evaluations validate the performance, efficiency, and traceability of our proposed framework, showcasing its superiority in handling complex feature transformation tasks.