Ronnie C. O. Alves

Lucas F. F. Cardoso, José de S. Ribeiro, Vitor C. A. Santos et al.

Intelligent systems that use Machine Learning classification algorithms are increasingly common in everyday society. However, many systems use black-box models that do not have characteristics that allow for self-explanation of their predictions. This situation leads researchers in the field and society to the following question: How can I trust the prediction of a model I cannot understand? In this sense, XAI emerges as a field of AI that aims to create techniques capable of explaining the decisions of the classifier to the end-user. As a result, several techniques have emerged, such as Explanation-by-Example, which has a few initiatives consolidated by the community currently working with XAI. This research explores the Item Response Theory (IRT) as a tool to explaining the models and measuring the level of reliability of the Explanation-by-Example approach. To this end, four datasets with different levels of complexity were used, and the Random Forest model was used as a hypothesis test. From the test set, 83.8% of the errors are from instances in which the IRT points out the model as unreliable.

Lucas F. F. Cardoso, Vitor C. A. Santos, Regiane S. Kawasaki Francês et al.

The experiments covered by Machine Learning (ML) must consider two important aspects to assess the performance of a model: datasets and algorithms. Robust benchmarks are needed to evaluate the best classifiers. For this, one can adopt gold standard benchmarks available in public repositories. However, it is common not to consider the complexity of the dataset when evaluating. This work proposes a new assessment methodology based on the combination of Item Response Theory (IRT) and Glicko-2, a rating system mechanism generally adopted to assess the strength of players (e.g., chess). For each dataset in a benchmark, the IRT is used to estimate the ability of classifiers, where good classifiers have good predictions for the most difficult test instances. Tournaments are then run for each pair of classifiers so that Glicko-2 updates performance information such as rating value, rating deviation and volatility for each classifier. A case study was conducted hereby which adopted the OpenML-CC18 benchmark as the collection of datasets and pool of various classification algorithms for evaluation. Not all datasets were observed to be really useful for evaluating algorithms, where only 10% were considered really difficult. Furthermore, the existence of a subset containing only 50% of the original amount of OpenML-CC18 was verified, which is equally useful for algorithm evaluation. Regarding the algorithms, the methodology proposed herein identified the Random Forest as the algorithm with the best innate ability.

Habib Asseiss Neto, Ronnie C. O. Alves, Sergio V. A. Campos

Designing adequate and precise neural architectures is a challenging task, often done by highly specialized personnel. AutoML is a machine learning field that aims to generate good performing models in an automated way. Spectral data such as those obtained from biological analysis have generally a lot of important information, and these data are specifically well suited to Convolutional Neural Networks (CNN) due to their image-like shape. In this work we present NASirt, an AutoML methodology based on Neural Architecture Search (NAS) that finds high accuracy CNN architectures for spectral datasets. The proposed methodology relies on the Item Response Theory (IRT) for obtaining characteristics from an instance level, such as discrimination and difficulty, and it is able to define a rank of top performing submodels. Several experiments are performed in order to demonstrate the methodology's performance with different spectral datasets. Accuracy results are compared to other benchmarks methods, such as a high performing, manually crafted CNN and the Auto-Keras AutoML tool. The results show that our method performs, in most cases, better than the benchmarks, achieving average accuracy as high as 97.40%.

Lucas F. F. Cardoso, Vitor C. A. Santos, Regiane S. K. Francês et al.

Despite the availability of benchmark machine learning (ML) repositories (e.g., UCI, OpenML), there is no standard evaluation strategy yet capable of pointing out which is the best set of datasets to serve as gold standard to test different ML algorithms. In recent studies, Item Response Theory (IRT) has emerged as a new approach to elucidate what should be a good ML benchmark. This work applied IRT to explore the well-known OpenML-CC18 benchmark to identify how suitable it is on the evaluation of classifiers. Several classifiers ranging from classical to ensembles ones were evaluated using IRT models, which could simultaneously estimate dataset difficulty and classifiers' ability. The Glicko-2 rating system was applied on the top of IRT to summarize the innate ability and aptitude of classifiers. It was observed that not all datasets from OpenML-CC18 are really useful to evaluate classifiers. Most datasets evaluated in this work (84%) contain easy instances in general (e.g., around 10% of difficult instances only). Also, 80% of the instances in half of this benchmark are very discriminating ones, which can be of great use for pairwise algorithm comparison, but not useful to push classifiers abilities. This paper presents this new evaluation methodology based on IRT as well as the tool decodIRT, developed to guide IRT estimation over ML benchmarks.