# Beyond Discrete Selection: Continuous Embedding Space Optimization for Generative Feature Selection

arXiv: https://arxiv.org/abs/2302.13221 · HTML: https://mlsanity.com/paper/2302.13221/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 36 references that are in the map.
- First posted on arXiv 26 Feb 2023.

## Builds on (most cited first, 7 of 7)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Feature Selection: A Data Perspective](https://mlsanity.com/paper/1601.07996/) (2016)
- [Group-wise Reinforcement Feature Generation for Optimal and Explainable Representation Space Reconstruction](https://mlsanity.com/paper/2205.14526/) (2022)
- [Traceable Automatic Feature Transformation via Cascading Actor-Critic Agents](https://mlsanity.com/paper/2212.13402/) (2022)
- [AutoFS: Automated Feature Selection via Diversity-aware Interactive Reinforcement Learning](https://mlsanity.com/paper/2008.12001/) (2020)
- [Efficient Reinforced Feature Selection via Early Stopping Traverse Strategy](https://mlsanity.com/paper/2109.14180/) (2021)

## Built on by (most cited first, 28 of 28)

- [A Comprehensive Survey on Data Augmentation](https://mlsanity.com/paper/2405.09591/) (2024)
- [Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions](https://mlsanity.com/paper/2309.13618/) (2023)
- [Feature Selection as Deep Sequential Generative Learning](https://mlsanity.com/paper/2403.03838/) (2024)
- [Knockoff-Guided Feature Selection via A Single Pre-trained Reinforced Agent](https://mlsanity.com/paper/2403.04015/) (2024)
- [Tabular Data Augmentation for Machine Learning: Progress and Prospects of Embracing Generative AI](https://mlsanity.com/paper/2407.21523/) (2024)
- [Neuro-Symbolic Embedding for Short and Effective Feature Selection via Autoregressive Generation](https://mlsanity.com/paper/2404.17157/) (2024)
- [Reinforcement Feature Transformation for Polymer Property Performance Prediction](https://mlsanity.com/paper/2409.15616/) (2024)
- [Resolving the Imbalance Issue in Hierarchical Disciplinary Topic Inference via LLM-based Data Augmentation](https://mlsanity.com/paper/2310.05318/) (2023)
- [Revolutionizing Biomarker Discovery: Leveraging Generative AI for Bio-Knowledge-Embedded Continuous Space Exploration](https://mlsanity.com/paper/2409.15612/) (2024)
- [FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-based Optimization](https://mlsanity.com/paper/2405.06312/) (2024)
- [Interdisciplinary Fairness in Imbalanced Research Proposal Topic Inference: A Hierarchical Transformer-based Method with Selective Interpolation](https://mlsanity.com/paper/2309.01717/) (2023)
- [GUME: Graphs and User Modalities Enhancement for Long-Tail Multimodal Recommendation](https://mlsanity.com/paper/2407.12338/) (2024)
- [Continuous Optimization for Feature Selection with Permutation-Invariant Embedding and Policy-Guided Search](https://mlsanity.com/paper/2505.11601/) (2025)
- [Feature Interaction Aware Automated Data Representation Transformation](https://mlsanity.com/paper/2309.17011/) (2023)
- [Autonomous Data Agents: A New Opportunity for Smart Data](https://mlsanity.com/paper/2509.18710/) (2025)
- [Enhancing Tabular Data Optimization with a Flexible Graph-based Reinforced Exploration Strategy](https://mlsanity.com/paper/2406.07404/) (2024)
- [FastFT: Accelerating Reinforced Feature Transformation via Advanced Exploration Strategies](https://mlsanity.com/paper/2503.20394/) (2025)
- [DELTA: Variational Disentangled Learning for Privacy-Preserving Data Reprogramming](https://mlsanity.com/paper/2509.00693/) (2025)
- [Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection](https://mlsanity.com/paper/2510.05535/) (2025)
- [Decoding Urban Industrial Complexity: Enhancing Knowledge-Driven Insights via IndustryScopeGPT](https://mlsanity.com/paper/2411.15758/) (2024)
- [DALL-M: Context-Aware Clinical Data Augmentation with LLMs](https://mlsanity.com/paper/2407.08227/) (2024)
- [Towards Data-Centric AI: A Comprehensive Survey of Traditional, Reinforcement, and Generative Approaches for Tabular Data Transformation](https://mlsanity.com/paper/2501.10555/) (2025)
- [Collaborative Multi-Agent Reinforcement Learning for Automated Feature Transformation with Graph-Driven Path Optimization](https://mlsanity.com/paper/2504.17355/) (2025)
- [Biological Pathway Guided Gene Selection Through Collaborative Reinforcement Learning](https://mlsanity.com/paper/2505.24155/) (2025)
- [Comprehend, Divide, and Conquer: Feature Subspace Exploration via Multi-Agent Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2504.17356/) (2025)
- [Dataforge: Agentic Platform for Autonomous Data Engineering](https://mlsanity.com/paper/2511.06185/) (2025)
- [Heterogeneous Multi-Agent Reinforcement Learning with Attention for Cooperative and Scalable Feature Transformation](https://mlsanity.com/paper/2511.21934/) (2025)
- [The Gold in Bias: Maturing the AI Design Process through Verification](https://mlsanity.com/paper/2609.29730/) (2026)

## Abstract (arXiv)

The goal of Feature Selection - comprising filter, wrapper, and embedded approaches - is to find the optimal feature subset for designated downstream tasks. Nevertheless, current feature selection methods are limited by: 1) the selection criteria of these methods are varied for different domains, making them hard to generalize; 2) the selection performance of these approaches drops significantly when processing high-dimensional feature space coupled with small sample size. In light of these challenges, we pose the question: can selected feature subsets be more robust, accurate, and input dimensionality agnostic? In this paper, we reformulate the feature selection problem as a deep differentiable optimization task and propose a new research perspective: conceptualizing discrete feature subsetting as continuous embedding space optimization. We introduce a novel and principled framework that encompasses a sequential encoder, an accuracy evaluator, a sequential decoder, and a gradient ascent optimizer. This comprehensive framework includes four important steps: preparation of features-accuracy training data, deep feature subset embedding, gradient-optimized search, and feature subset reconstruction. Specifically, we utilize reinforcement feature selection learning to generate diverse and high-quality training data and enhance generalization. By optimizing reconstruction and accuracy losses, we embed feature selection knowledge into a continuous space using an encoder-evaluator-decoder model structure. We employ a gradient ascent search algorithm to find better embeddings in the learned embedding space. Furthermore, we reconstruct feature selection solutions using these embeddings and select the feature subset with the highest performance for downstream tasks as the optimal subset.