# MEL: Efficient Multi-Task Evolutionary Learning for High-Dimensional Feature Selection

arXiv: https://arxiv.org/abs/2402.08982 · HTML: https://mlsanity.com/paper/2402.08982/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 82 references that are in the map.
- First posted on arXiv 14 Feb 2024.

## Builds on (most cited first, 6 of 6)

- [Gradient Surgery for Multi-Task Learning](https://mlsanity.com/paper/2001.06782/) (2020)
- [A Survey on Multi-Task Learning](https://mlsanity.com/paper/1707.08114/) (2017)
- [UniT: Multimodal Multitask Learning with a Unified Transformer](https://mlsanity.com/paper/2102.10772/) (2021)
- [A Multitask Learning Approach for Diacritic Restoration](https://mlsanity.com/paper/2006.04016/) (2020)
- [A Self-adaptive Weighted Differential Evolution Approach for Large-scale Feature Selection](https://mlsanity.com/paper/2110.14166/) (2021)
- [Flower Pollination Algorithm: A Novel Approach for Multiobjective Optimization](https://mlsanity.com/paper/1408.5332/) (2014)

## Built on by (most cited first, 6 of 6)

- [Continuous Optimization for Feature Selection with Permutation-Invariant Embedding and Policy-Guided Search](https://mlsanity.com/paper/2505.11601/) (2025)
- [Permutation-Invariant Representation Learning for Robust and Privacy-Preserving Feature Selection](https://mlsanity.com/paper/2510.05535/) (2025)
- [SurvBench: A Standardised Preprocessing Pipeline for Multi-Modal Electronic Health Record Survival Analysis](https://mlsanity.com/paper/2511.11935/) (2025)
- [Iterative Feature Space Optimization through Incremental Adaptive Evaluation](https://mlsanity.com/paper/2501.14889/) (2025)
- [Meta-Sel: Efficient Demonstration Selection for In-Context Learning via Supervised Meta-Learning](https://mlsanity.com/paper/2602.12123/) (2026)
- [Geometric Manifold Rectification for Imbalanced Learning](https://mlsanity.com/paper/2602.13045/) (2026)

## Abstract (arXiv)

Feature selection is a crucial step in data mining to enhance model performance by reducing data dimensionality. However, the increasing dimensionality of collected data exacerbates the challenge known as the "curse of dimensionality", where computation grows exponentially with the number of dimensions. To tackle this issue, evolutionary computational (EC) approaches have gained popularity due to their simplicity and applicability. Unfortunately, the diverse designs of EC methods result in varying abilities to handle different data, often underutilizing and not sharing information effectively. In this paper, we propose a novel approach called PSO-based Multi-task Evolutionary Learning (MEL) that leverages multi-task learning to address these challenges. By incorporating information sharing between different feature selection tasks, MEL achieves enhanced learning ability and efficiency. We evaluate the effectiveness of MEL through extensive experiments on 22 high-dimensional datasets. Comparing against 24 EC approaches, our method exhibits strong competitiveness. Additionally, we have open-sourced our code on GitHub at https://github.com/wangxb96/MEL.