Dual-Agent Reinforcement Learning for Automated Feature Generation

TL;DR

This paper introduces a dual-agent reinforcement learning approach with self-attention and feature-type differentiation to improve feature generation, reducing redundancy and capturing complex relationships for better machine learning performance.

Contribution

It presents a novel dual-agent RL framework with enhanced state representation and feature-type handling, addressing key challenges in feature generation.

Findings

Effective in reducing redundant features

Improves model performance across datasets

Outperforms existing feature generation methods

Abstract

Feature generation involves creating new features from raw data to capture complex relationships among the original features, improving model robustness and machine learning performance. Current methods using reinforcement learning for feature generation have made feature exploration more flexible and efficient. However, several challenges remain: first, during feature expansion, a large number of redundant features are generated. When removing them, current methods only retain the best features each round, neglecting those that perform poorly initially but could improve later. Second, the state representation used by current methods fails to fully capture complex feature relationships. Third, there are significant differences between discrete and continuous features in tabular data, requiring different operations for each type. To address these challenges, we propose a novel dual-agent reinforcement learning method for feature generation. Two agents are designed: the first generates new features, and the second determines whether they should be preserved. A self-attention mechanism enhances state representation, and diverse operations distinguish interactions between discrete and continuous features. The experimental results on multiple datasets demonstrate that the proposed method is effective. The code is available at https://github.com/extess0/DARL.