Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning
This work addresses the problem of scalable and efficient feature selection for machine learning practitioners, offering an incremental improvement over current reinforcement learning approaches.
The paper tackles the challenge of inefficient feature selection in complex datasets by proposing HRLFS, a multi-agent hierarchical reinforcement learning approach that clusters features and uses hierarchical agents, which improves downstream ML performance and accelerates runtime compared to existing RL-based methods.
Feature selection aims to preprocess the target dataset, find an optimal and most streamlined feature subset, and enhance the downstream machine learning task. Among filter, wrapper, and embedded-based approaches, the reinforcement learning (RL)-based subspace exploration strategy provides a novel objective optimization-directed perspective and promising performance. Nevertheless, even with improved performance, current reinforcement learning approaches face challenges similar to conventional methods when dealing with complex datasets. These challenges stem from the inefficient paradigm of using one agent per feature and the inherent complexities present in the datasets. This observation motivates us to investigate and address the above issue and propose a novel approach, namely HRLFS. Our methodology initially employs a Large Language Model (LLM)-based hybrid state extractor to capture each feature's mathematical and semantic characteristics. Based on this information, features are clustered, facilitating the construction of hierarchical agents for each cluster and sub-cluster. Extensive experiments demonstrate the efficiency, scalability, and robustness of our approach. Compared to contemporary or the one-feature-one-agent RL-based approaches, HRLFS improves the downstream ML performance with iterative feature subspace exploration while accelerating total run time by reducing the number of agents involved.