Luís Paulo Faina Garcia
He is a professor in the Computer Science Department at the University of Brasília - Brazil. His research interests include Machine Learning, Data Mining, Data Streams and Meta-Learning
Contact
luis [dot] garcia [at] unb [dot] brlpfgarcia [at] gmail [dot] com
About
Luís Paulo Faina Garcia received a BSc. degree in Computer Engineering in 2010 and a Ph.D. in Computer Science in 2016 from University of São Paulo, Brazil. In 2017, he received two awards for best thesis from the Brazilian Government Council (CAPES) and the Brazilian Computer Society (SBC). He is currently a professor in the Computer Science Department - University of Brasília, Brazil. His research interests include Machine Learning, Data Mining, Data Streams and Meta-Learning.
Education
- 2019: Professor - University of Brasilia
- 2018 - 2019: Postdoctoral Researcher - University of São Paulo
- 2017 - 2018: Postdoctoral Researcher - Leipzig University
- 2011 - 2016: Ph.D. in Computer Science - University of São Paulo
- 2006 - 2010: BSc. degree in Computer Engineering - University of São Paulo
Last main publications
- RIVOLLI, A., GARCIA, L. P. F., SOARES, C., VANSCHOREN, J., CARVALHO, A. C. P. L. F. Meta-features for meta-learning. Knowledge-Based Systems, v. 240, p. 108101, 2022.
- SA, J. M. C., ROSSI, A. L. D., BATISTA, G. E. A. P. A., GARCIA, L. P. F. Algorithm Recommendation for Data Streams. In: 25th International Conference on Pattern Recognition, 2021. International Conference on Pattern Recognition, 2021.
- ALCOBACA, E., SIQUEIRA, F., RIVOLLI, A., GARCIA, L. P. F., OLIVA, J. T., DE CARVALHO, A. C. P. L. F. MFE: Towards reproducible meta-feature extraction. JOURNAL OF MACHINE LEARNING RESEARCH (ONLINE), v. 21, p. 1-5, 2020.
- OLIVEIRA, I. L., FILETO, R., SPECK, R., GARCIA, L. P. F., MOUSSALLEM, D., LEHMANN, J. Towards holistic Entity Linking: Survey and directions. INFORMATION SYSTEMS, v. 95, p. 101624, 2020.
- LORENA, A. C., GARCIA, L. P. F., LEHMANN, J., SOUTO, M. C. P., HO, T. K. How Complex Is Your Classification Problem?. ACM COMPUTING SURVEYS, v. 52, p. 1-34, 2019.
Last Projects
- KnEDLe - Knowledge Extraction from Documents of Legal content
- HCIA-AI: HUAWEI AI certification
- Brasília Living Labs
Skills
- I have been working with Artificial Intelligence Machine Learning since 2008. I started studying algorithms capable of detecting label noise in batch dataset problems. After that, I migrated to recommendation systems based on meta-learning and how to characterize classification datasets. In the last few years, I have been working with stream problems. In this field, the main scenarios are one-class classification to detect rare classes and concept drift.
- Python, Scala, and R are my main programming languages. I have been using R since 2008, mostly for prototyping. A few years later, I was introduced to Scala. Scala and Java were the most used language used for representation learning. In this matter, I worked with link prediction based on Knowledge Graphs Embedding techniques. In the last 10 years, I have focused on Python and R.
- I have proposed many packages and libraries in R and Python in recent years. I also use tools like mlflow, prefect, sklearn, and Keras, adapting them to my projects.