Abstract
It is recognised that the imbalanced data problem is aggravated by other difficulty factors, such as class overlap. Over the years, several research works have focused on this problematic, although presenting two major hitches: the limitation of test domains and the lack of a formulation of the overlap degree, which makes results hard to generalise. This work studies the performance degradation of classifiers with distinct learning biases in overlap and imbalanced contexts, focusing on the characteristics of the test domains (shape, dimensionality and imbalance ratio) and on to what extent our proposed overlapping measure (degOver) is aligned with the performance results observed. Our results show that MLP and CART classifiers are the most robust to high levels of class overlap, even for complex domains, and that KNN and linear SVM are the most aligned with degOver. Furthermore, we found that the dimensionality of data also plays an important role in explaining performance results. © Springer Nature Switzerland AG 2018.

Abstract

Abstract
Missing data is a problem found in real-world datasets that has a considerable impact on the learning process of classifiers. Although extensive work has been done in this field, the MNAR mechanism still remains a challenge for the existing imputation methods, mainly because it is not related with any observed information. Focusing on healthcare contexts, MNAR is present in multiple scenarios such as clinical trials where the participants may be quitting the study for reasons related to the outcome that is being measured. This work proposes an approach that uses different sources of information from the same healthcare context to improve the imputation quality and classification performance for datasets with missing data under MNAR. The experiment was performed with several databases from the medical context and the results show that the use of multiple sources of data has a positive impact in the imputation error and classification performance. © 2019, Springer Nature Switzerland AG.

Abstract
Missing data is a problem often found in real-world datasets and it can degrade the performance of most machine learning models. Several deep learning techniques have been used to address this issue, and one of them is the Autoencoder and its Denoising and Variational variants. These models are able to learn a representation of the data with missing values and generate plausible new ones to replace them. This study surveys the use of Autoencoders for the imputation of tabular data and considers 26 works published between 2014 and 2020. The analysis is mainly focused on discussing patterns and recommendations for the architecture, hyperparameters and training settings of the network, while providing a detailed discussion of the results obtained by Autoencoders when compared to other state-of-the-art methods, and of the data contexts where they have been applied. The conclusions include a set of recommendations for the technical settings of the network, and show that Denoising Autoencoders outperform their competitors, particularly the often used statistical methods.

Abstract
Current research on imbalanced data recognises that class imbalance is aggravated by other data intrinsic characteristics, among which class overlap stands out as one of the most harmful. The combination of these two problems creates a new and difficult scenario for classification tasks and has been discussed in several research works over the past two decades. In this paper, we argue that despite some insightful information can be derived from related research, the joint-effect of class overlap and imbalance is still not fully understood, and advocate for the need to move towards a unified view of the class overlap problem in imbalanced domains. To that end, we start by performing a thorough analysis of existing literature on the joint-effect of class imbalance and overlap, elaborating on important details left undiscussed on the original papers, namely the impact of data domains with different characteristics and the behaviour of classifiers with distinct learning biases. This leads to the hypothesis that class overlap comprises multiple representations, which are important to accurately measure and analyse in order to provide a full characterisation of the problem. Accordingly, we devise two novel taxonomies, one for class overlap measures and the other for class overlap-based approaches, both resonating with the distinct representations of class overlap identified. This paper therefore presents a global and unique view on the joint-effect of class imbalance and overlap, from precursor work to recent developments in the field. It meticulously discusses some concepts taken as implicit in previous research, explores new perspectives in light of the limitations found, and presents new ideas that will hopefully inspire researchers to move towards a unified view on the problem and the development of suitable strategies for imbalanced and overlapped domains.

Abstract
Cybersecurity attacks, such as poisoning and evasion, can intentionally introduce false or misleading information in different forms into data, potentially leading to catastrophic consequences for critical infrastructures, like water supply or energy power plants. While numerous studies have investigated the impact of these attacks on model-based prediction approaches, they often overlook the impurities present in the data used to train these models. One of those forms is missing data, the absence of values in one or more features. This issue is typically addressed by imputing missing values with plausible estimates, which directly impacts the performance of the classifier. The goal of this work is to promote a Data-centric AI approach by investigating how different types of cybersecurity attacks impact the imputation process. To this end, we conducted experiments using four popular evasion and poisoning attacks strategies across 29 real-world datasets, including the NSL-KDD and Edge-IIoT datasets, which were used as case study. For the adversarial attack strategies, we employed the Fast Gradient Sign Method, Carlini & Wagner, Project Gradient Descent, and Poison Attack against Support Vector Machine algorithm. Also, four state-of-the-art imputation strategies were tested under Missing Not At Random, Missing Completely at Random, and Missing At Random mechanisms using three missing rates (5%, 20%, 40%). We assessed imputation quality using MAE, while data distribution shifts were analyzed with the Kolmogorov-Smirnov and Chi-square tests. Furthermore, we measured classification performance by training an XGBoost classifier on the imputed datasets, using F1-score, Accuracy, and AUC. To deepen our analysis, we also incorporated six complexity metrics to characterize how adversarial attacks and imputation strategies impact dataset complexity. Our findings demonstrate that adversarial attacks significantly impact the imputation process. In terms of imputation assessment in what concerns to quality error, the scenario that enrolees imputation with Project Gradient Descent attack proved to be more robust in comparison to other adversarial methods. Regarding data distribution error, results from the Kolmogorov-Smirnov test indicate that in the context of numerical features, all imputation strategies differ from the baseline (without missing data) however for the categorical context Chi-Squared test proved no difference between imputation and the baseline.