Noise Labels in Machine Learning: Evaluation measures and machine learning algorithms

• Grant number: 15/20606-6
• Support Opportunities: Scholarships abroad - Research
• Start date: April 01, 2016
• End date: March 31, 2017
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Ronaldo Cristiano Prati
• Grantee: Ronaldo Cristiano Prati
• Host Investigator: Francisco Herrera
• Host Institution: Centro de Matemática, Computação e Cognição (CMCC). Universidade Federal do ABC (UFABC). Ministério da Educação (Brasil). Santo André , SP, Brazil
• Institution abroad: Universidad de Granada (UGR), Spain

Abstract

Supervised Machine Learning aims to automatically build classification models from a set o labeled data. However, highly quality labeled data is not available in numerous real world problems, an issue known as label noise. This label noise may cause numerous problems for Machine Learning algorithms. Although some research has been conducted in the model generation phase, few studies focus on the evaluation process in presence of noise labels. This is an important research topic, as Machine Learning research is based on empirical studies, and misleading conclusions may be drawn when comparing learning algorithms in class noise context. This research proposal aims to investigate this open-ended topic, developing a systematic study regarding the influence of some class-noise patterns in the evaluation phase of the machine learning process.

Scientific publications

(4)

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

PRATI, RONALDO C.; CHARTE, FRANCISCO; HERRERA, FRANCISCO; IEEE. A first approach towards a fuzzy decision tree for multilabel classification. 2017 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ-IEEE), v. N/A, p. 6-pg., 2017-01-01. (15/20606-6)

LUENGO, JULIAN; SANCHEZ-TARRAGO, DANEL; PRATI, RONALDO C.; HERRERA, FRANCISCO. Multiple instance classification: Bag noise filtering for negative instance noise cleaning. INFORMATION SCIENCES, v. 579, p. 388-400, NOV 2021. (15/20606-6)

PRATI, RONALDO C.; LUENGO, JULIAN; HERRERA, FRANCISCO. Emerging topics and challenges of learning from noisy data in nonstandard classification: a survey beyond binary class noise. KNOWLEDGE AND INFORMATION SYSTEMS, v. 60, n. 1, p. 63-97, JUL 2019. (15/20606-6)

FARIAS, DELIA IRAZU HERNANDEZ; PRALI, RONALDO; HERRERA, FRANCISCO; ROSSO, PAOLO. Irony detection in Twitter with imbalanced class distributions. JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, v. 39, n. 2, p. 2147-2163, 2020. (15/20606-6)