paper-with-me

홈 › Papers

Dynamic Design of Machine Learning Pipelines via Metalearning

2025-08-19 · Edesio Alcobaça, André C. P. L. F. de Carvalho arxiv

Automated machine learning (AutoML) has democratized the design of machine learning based systems, by automating model selection, hyperparameter tuning and feature engineering. However, the high computational cost associated with traditional search and optimization strategies, such as Random Search, Particle Swarm Optimization and Bayesian Optimization, remains a significant challenge. Moreover, AutoML systems typically explore a large search space, which can lead to overfitting. This paper introduces a metalearning method for dynamically designing search spaces for AutoML system. The proposed method uses historical metaknowledge to select promising regions of the search space, accelerating the optimization process. According to experiments conducted for this study, the proposed method can reduce runtime by 89\% in Random Search and search space by (1.8/13 preprocessor and 4.3/16 classifier), without compromising significant predictive performance. Moreover, the proposed method showed competitive performance when adapted to Auto-Sklearn, reducing its search space. Furthermore, this study encompasses insights into meta-feature selection, meta-model explainability, and the trade-offs inherent in search space reduction strategies.

📄 PDF Abstract BibTeX arXiv:2508.13436

Code (0)

등록된 구현이 없습니다.

Tasks

Feature Engineering

Similar Papers 제목 키워드 기반

Preprocessor Selection for Machine Learning Pipelines

2018-10-23 · Brandon Schoenfeld, Christophe Giraud-Carrier, Mason Poggemann, Jarom Christensen 외

Much of the work in metalearning has focused on classifier selection, combined more recently with hyperparameter optimization, with little concern for data preprocessing. Yet, it is generally well accepted that machine l…

BIG-bench Machine LearningHyperparameter Optimization

A Metalearning Approach for Physics-Informed Neural Networks (PINNs): Application to Parameterized PDEs

2021-10-26 · Michael Penwarden, Shandian Zhe, Akil Narayan, Robert M. Kirby

Physics-informed neural networks (PINNs) as a means of discretizing partial differential equations (PDEs) are garnering much attention in the Computational Science and Engineering (CS&E) world. At least two challenges ex…

BIG-bench Machine LearningPhysics-informed machine learningTransfer Learning

MetaMT,a MetaLearning Method Leveraging Multiple Domain Data for Low Resource Machine Translation

2019-12-11 · Rumeng Li, Xun Wang, Hong Yu

Manipulating training data leads to robust neural models for MT.

Machine TranslationTranslation

Rapid Adaptation with Conditionally Shifted Neurons

2017-12-28 · ICML 2018 7 · Tsendsuren Munkhdalai, Xingdi Yuan, Soroush Mehri, Adam Trischler

We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons. We apply this mechani…

Few-Shot Image Classification

Metalearning for Feature Selection

2017-03-20 · Ben Goertzel, Nil Geisweiller, Chris Poulin

A general formulation of optimization problems in which various candidate solutions may use different feature-sets is presented, encompassing supervised classification, automated program learning and other cases. A novel…

Classificationfeature selectionGeneral Classificationtext-classification+1