MFE: Towards reproducible meta-feature extraction

被引:0
作者
Alcobaca, Edesio [1 ]
Siqueira, Felipe [1 ]
Rivolli, Adriano [1 ]
Garcia, Luis P. F. [1 ]
Oliva, Jefferson T. [1 ]
de Carvalho, Andre C. P. L. F. [1 ]
机构
[1] Univ Sao Paulo, Inst Math & Comp Sci, Av Trabalhador Sao Carlense 400, BR-13560970 Sao Carlos, SP, Brazil
基金
巴西圣保罗研究基金会;
关键词
Machine Learning; AutoML; Meta-Learning; Meta-Features; SELECTION;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Automated recommendation of machine learning algorithms is receiving a large deal of attention, not only because they can recommend the most suitable algorithms for a new task, but also because they can support efficient hyper-parameter tuning, leading to better machine learning solutions. The automated recommendation can be implemented using meta-learning, learning from previous learning experiences, to create a meta-model able to associate a data set to the predictive performance of machine learning algorithms. Although a large number of publications report the use of meta-learning, reproduction and comparison of meta-learning experiments is a difficult task. The literature lacks extensive and comprehensive public tools that enable the reproducible investigation of the different meta-learning approaches. An alternative to deal with this difficulty is to develop a meta-feature extractor package with the main characterization measures, following uniform guidelines that facilitate the use and inclusion of new meta-features. In this paper, we propose two Meta-Feature Extractor (MFE) packages, written in both Python and R, to fill this lack. The packages follow recent frameworks for meta-feature extraction, aiming to facilitate the reproducibility of meta-learning experiments.
引用
收藏
页数:5
相关论文
共 50 条
[31]   Robust Discriminant Regression for Feature Extraction [J].
Lai, Zhihui ;
Mo, Dongmei ;
Wong, Wai Keung ;
Xu, Yong ;
Miao, Duoqian ;
Zhang, David .
IEEE TRANSACTIONS ON CYBERNETICS, 2018, 48 (08) :2472-2484
[32]   Feature Extraction for Hyperspectral Image Classification [J].
Uddin, M. P. ;
Mamun, M. A. ;
Hossain, M. A. .
2017 IEEE REGION 10 HUMANITARIAN TECHNOLOGY CONFERENCE (R10-HTC), 2017, :379-382
[33]   Trends in biomedical signal feature extraction [J].
Krishnan, Sridhar ;
Athavale, Yashodhan .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2018, 43 :41-63
[34]   EDISON: Feature Extraction for NLP, Simplified [J].
Sammons, Mark ;
Christodoulopoulos, Christos ;
Kordjamshidi, Parisa ;
Khashabi, Daniel ;
Srikumar, Vivek ;
Vijayakumar, Paul ;
Bokhari, Mazin ;
Wu, Xinbo ;
Roth, Dan .
LREC 2016 - TENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2016, :4085-4092
[35]   Feature Extraction and Classification of Spam Emails [J].
Hassan, Muhammad Ali ;
Mtetwa, Nhamo .
2018 5TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING & MACHINE INTELLIGENCE (ISCMI), 2018, :93-98
[36]   Feature Extraction and Classification of Movie Reviews [J].
Mtetwa, Nhamo ;
Awukam, Awukam Ojang ;
Yousefi, Mehdi .
2018 5TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING & MACHINE INTELLIGENCE (ISCMI), 2018, :67-71
[37]   A Fusion of Feature Extraction and Feature Selection Technique for Network Intrusion Detection [J].
Hamid, Yasir ;
Sugumaran, M. ;
Journaux, Ludovic .
INTERNATIONAL JOURNAL OF SECURITY AND ITS APPLICATIONS, 2016, 10 (08) :151-158
[38]   A Comparison of Feature Selection and Feature Extraction in Network Intrusion Detection Systems [J].
Vuong, Tuan-Cuong ;
Tran, Hung ;
Trang, Mai Xuan ;
Ngo, Vu-Duc ;
Van Luong, Thien .
PROCEEDINGS OF 2022 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2022, :1798-1804
[39]   Automating Feature Extraction and Feature Selection in Big Data Security Analytics [J].
Sisiaridis, Dimitrios ;
Markowitch, Olivier .
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING (ICAISC 2018), PT II, 2018, 10842 :423-432
[40]   Comparison of different feature extraction methods for EEG-based emotion recognition [J].
Nawaz, Rab ;
Cheah, Kit Hwa ;
Nisar, Humaira ;
Yap, Vooi Voon .
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING, 2020, 40 (03) :910-926