Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning
Open Access
- 5 September 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Knowledge Discovery From Data
- Vol. 20 (8) , 1-25
Abstract
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 one-feature-one-agent RL-based approaches, HRLFS improves the downstream ML performance with iterative feature subspace exploration while accelerating total runtime by reducing the number of agents involved. Our code and dataset are publicly accessible on GitHub and Huggingface .Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62506351, 92470204)
- Strategic Priority Research Program of the Chinese Academy of Sciences (XDB1350102)
- Beijing Natural Science Foundation (4254089)
This publication has 40 references indexed in Scilit:
- Reinforcement learning guided auto-select optimization algorithm for feature selectionExpert Systems with Applications, 2025
- Advances, challenges and opportunities in creating data for trustworthy AINature Machine Intelligence, 2022
- Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms2021
- Ensemble of feature selection algorithms: a multi-criteria decision-making approachInternational Journal of Machine Learning and Cybernetics, 2021
- Feature clustering based support vector machine recursive feature elimination for gene selectionApplied Intelligence, 2017
- Recent advances in feature selection and its applicationsKnowledge and Information Systems, 2017
- Feature subset selection in large dimensionality domainsPattern Recognition, 2010
- A tutorial on spectral clusteringStatistics and Computing, 2007
- Hierarchical multi-agent reinforcement learningAutonomous Agents and Multi-Agent Systems, 2006
- Hierarchical Grouping to Optimize an Objective FunctionJournal of the American Statistical Association, 1963