MLStar A System for Synthesis of Machine-Learning Programs

被引：1

作者：

Kopito, Gabriel ^{[1
]}

Amblard, Julien ^{[1
]}

Filman, Robert ^{[1
]}

Rabern, Landon ^{[1
]}

Schwartz, Jonathan ^{[1
]}

机构：

[1] PerformanceStar, Santa Clara, CA 95051 USA

来源：

PROCEEDINGS OF THE 2023 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION, GECCO 2023 COMPANION | 2023年

关键词：

genetic programming; directed acyclic graphs; ScikitLearn; Auto-ML;

D O I：

10.1145/3583133.3596367

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper introduces our auto-ML system, MLStar, which uses genetic programming to create scikit-learn and Keras-based Python programs to perform supervised learning. MLStar leverages our own genetic programming system (GPStar4) and provides a greater search space compared to traditional genetic programming frameworks. Key elements that enable MLStar's performance include representing individuals as Directed Acyclic Graphs (DAGs), a rich type system to shape the kinds of graphs generated, novel genetic operators which work on the DAG structure, and advanced hyperparameter tuning via the Optuna hyperparameter optimization framework. MLStar also offers multiobjective fitnesses and a variety of complex population types. We show that MLStar performs favorably to several other auto-ML frameworks on benchmark tests. We also demonstrate that MLStar is capable of competitive solutions even when running with computationally expensive features disabled.

引用

页码：1721 / 1726

页数：6

共 50 条

[31] Machine-learning mathematical structures
He, Yang-Hui
arXiv, 2021,
[32] Machine Learning for Testing Machine-Learning Hardware: A Virtuous Cycle
Chaudhuri, Arjun
Talukdar, Jonti
Chakrabarty, Krishnendu
2022 IEEE/ACM INTERNATIONAL CONFERENCE ON COMPUTER AIDED DESIGN, ICCAD, 2022,
[33] Semi-supervised machine-learning classification of materials synthesis procedures
Haoyan Huo
Ziqin Rong
Olga Kononova
Wenhao Sun
Tiago Botari
Tanjin He
Vahe Tshitoyan
Gerbrand Ceder
npj Computational Materials, 5
[34] Machine-learning rationalization and prediction of solid-state synthesis conditions
Huo, Haoyan
Bartel, Christopher J.
He, Tanjin
Trewartha, Amalie
Dunn, Alexander
Ouyang, Bin
Jain, Anubhav
Ceder, Gerbrand
arXiv, 2022,
[35] Semi-supervised machine-learning classification of materials synthesis procedures
Huo, Haoyan
Rong, Ziqin
Kononova, Olga
Sun, Wenhao
Botari, Tiago
He, Tanjin
Tshitoyan, Vahe
Ceder, Gerbrand
NPJ COMPUTATIONAL MATERIALS, 2019, 5 (1)
[36] Machine-Learning Rationalization and Prediction of Solid-State Synthesis Conditions
Huo, Haoyan
Bartel, Christopher J.
He, Tanjin
Trewartha, Amalie
Dunn, Alexander
Ouyang, Bin
Jain, Anubhav
Ceder, Gerbrand
CHEMISTRY OF MATERIALS, 2022, 34 (16) : 7323 - 7336
[37] How can machine-learning methods assist in virtual screening for hyperuricemia? A healthcare machine-learning approach
Ichikawa, Daisuke
Saito, Toki
Ujita, Waka
Oyama, Hiroshi
JOURNAL OF BIOMEDICAL INFORMATICS, 2016, 64 : 20 - 24
[38] A design method of machine-learning system used for autonomous land vehicle
Hangen, H
Wensen, C
UNMANNED GROUND VEHICLE TECHNOLOGY, 1999, 3693 : 282 - 289
[39] A Robust and Fast Data Management System for Machine-Learning Research of Tokamaks
Wan, Chenguang
Yu, Zhi
Liu, Xiaojuan
Wen, Xinghao
Deng, Xi
Li, Jiangang
IEEE TRANSACTIONS ON PLASMA SCIENCE, 2022, 50 (12) : 4980 - 4986
[40] Intelligent System to Detect Malicious URLs Using Machine-Learning Algorithms
Jeyavadhanam, B. Rebecca
Bhuvanan, Mahesh
Sihan, Haroon
Ahmadzadeh, Sahar
Karthick, Gayathri
PROCEEDINGS OF NINTH INTERNATIONAL CONGRESS ON INFORMATION AND COMMUNICATION TECHNOLOGY, VOL 2, ICICT 2024, 2024, 1012 : 349 - 358

← 1 2 3 4 5 →