3 papers
cs.LG2025
Beyond Random Sampling: Instance Quality-Based Data Partitioning via Item Response Theory
Lucas Cardoso, Vitor Santos, José Ribeiro Filho +3
Robust validation of Machine Learning (ML) models is essential, but traditional data partitioning approaches often ignore the intrinsic quality of each instance. This study propose…
cs.LG2025
Enhancing Classifier Evaluation: A Fairer Benchmarking Strategy Based on Ability and Robustness
Lucas Cardoso, Vitor Santos, José Ribeiro +3
Benchmarking is a fundamental practice in machine learning (ML) for comparing the performance of classification algorithms. However, traditional evaluation methods often overlook a…
cs.LG2024
How Reliable and Stable are Explanations of XAI Methods?
José Ribeiro, Lucas Cardoso, Vitor Santos +3
Black box models are increasingly being used in the daily lives of human beings living in society. Along with this increase, there has been the emergence of Explainable Artificial…