The most important part of model selection and hyperparameter tuning is the evaluation of model performance. The most popular measures, such as AUC, F1, ACC for binary classification, or RMSE, MAD for regression, or cross-entropy for multilabel classification share two common weaknesses. First is, that they are not on an interval scale. It means that the difference in performance for the two models has no direct interpretation. It makes no sense to compare such differences between datasets. Second is, that for k-fold cross-validation, the model performance is in most cases calculated as an average performance from particular folds, which neglects the information how stable is the performance for different folds. In this talk, we introduce a new EPP rating system for predictive models. We also demonstrate numerous advantages for this system, First, differences in EPP scores have probabilistic interpretation. Based on it we can assess the probability that one model will achieve better performance than another. Second, EPP scores can be directly compared between datasets. Third, they can be used for navigated hyperparameter tuning and model selection. Forth, we can create embeddings for datasets based on EPP scores.

In this paper, we advocate for the study of fairness techniques in low data situations. We propose two algorithms Fairness Warnings and Fair-MAML. The first is a model-agnostic algorithm that provides interpretable boundary conditions for when a fairly trained model may not behave fairly on similar but slightly different tasks within a given domain. The second is a fair meta-learning approach to train models that can be trained through gradient descent with the objective of "learning how to learn fairly". This method encodes more general notions of fairness and accuracy into the model so that it can learn new tasks within a domain both quickly and fairly from only a few training points. We demonstrate experimentally the individual utility of each model using relevant baselines for comparison and provide the first experiment to our knowledge of K-shot fairness, i.e. training a fair model on a new task with only K data points. Then, we illustrate the usefulness of both algorithms as a combined method for training models from a few data points on new tasks while using Fairness Warnings as interpretable boundary conditions under which the newly trained model may not be fair.

Background: While machine learning (ML) models are rapidly emerging as promising screening tools in critical care medicine, the identification of homogeneous subphenotypes within populations with heterogeneous conditions such as pediatric sepsis may facilitate attainment of high-predictive performance of these prognostic algorithms. This study is aimed to identify subphenotypes of pediatric sepsis and demonstrate the potential value of partitioned data/subtyping-based training. Methods: This was a retrospective study of clinical data extracted from medical records of 6,446 pediatric patients that were admitted at a major hospital system in the DC area. Vitals and labs associated with patients meeting the diagnostic criteria for sepsis were used to perform latent profile analysis. Modern ML algorithms were used to explore the predictive performance benefits of reduced training data heterogeneity via label profiling. Results: In total 134 (2.1%) patients met the diagnostic criteria for sepsis in this cohort and latent profile analysis identified four profiles/subphenotypes of pediatric sepsis. Profiles 1 and 3 had the lowest mortality and included pediatric patients from different age groups. Profile 2 were characterized by respiratory dysfunction; profile 4 by neurological dysfunction and highest mortality rate (22.2%). Machine learning experiments comparing the predictive performance of models derived without training data profiling against profile targeted models suggest statistically significant improved performance of prediction can be obtained. For example, area under ROC curve (AUC) obtained to predict profile 4 with 24-hour data (AUC = .998, p < .0001) compared favorably with the AUC obtained from the model considering all profiles as a single homogeneous group (AUC = .918) with 24-hour data.

We propose a novel classifier accuracy metric: the Bayesian Area Under the Receiver Operating Characteristic Curve (CBAUC). The method estimates the area under the ROC curve and is related to the recently proposed Bayesian Error Estimator. The metric can assess the quality of a classifier using only the training dataset without the need for computationally expensive cross-validation. We derive a closed-form solution of the proposed accuracy metric for any linear binary classifier under the Gaussianity assumption, and study the accuracy of the proposed estimator using simulated and real-world data. These experiments confirm that the closed-form CBAUC is both faster and more accurate than conventional AUC estimators.

The Synthetic Minority Oversampling TEchnique (SMOTE) is widely-used for the analysis of imbalanced datasets. It is known that SMOTE frequently over-generalizes the minority class, leading to misclassifications for the majority class, and effecting the overall balance of the model. In this article, we present an approach that overcomes this limitation of SMOTE, employing Localized Random Affine Shadowsampling (LoRAS) to oversample from an approximated data manifold of the minority class. We benchmarked our LoRAS algorithm with 28 publicly available datasets and show that that drawing samples from an approximated data manifold of the minority class is the key to successful oversampling. We compared the performance of LoRAS, SMOTE, and several SMOTE extensions and observed that for imbalanced datasets LoRAS, on average generates better Machine Learning (ML) models in terms of F1-score and Balanced Accuracy. Moreover, to explain the success of the algorithm, we have constructed a mathematical framework to prove that LoRAS is a more effective oversampling technique since it provides a better estimate to mean of the underlying local data distribution of the minority class data space.

[Context:] Model-based testing is an instrument for automated generation of test cases. It requires identifying requirements in documents, understanding them syntactically and semantically, and then translating them into a test model. One light-weight language for these test models are Cause-Effect-Graphs (CEG) that can be used to derive test cases. [Problem:] The creation of test models is laborious and we lack an automated solution that covers the entire process from requirement detection to test model creation. In addition, the majority of requirements is expressed in natural language (NL), which is hard to translate to test models automatically. [Principal Idea:] We build on the fact that not all NL requirements are equally unstructured. We found that 14 % of the lines in requirements documents of our industry partner contain "pseudo-code"-like descriptions of business rules. We apply Machine Learning to identify such semi-structured requirements descriptions and propose a rule-based approach for their translation into CEGs. [Contribution:] We make three contributions: (1) an algorithm for the automatic detection of semi-structured requirements descriptions in documents, (2) an algorithm for the automatic translation of the identified requirements into a CEG and (3) a study demonstrating that our proposed solution leads to 86 % time savings for test model creation without loss of quality.

Systematic reviews, which summarize and synthesize all the current research in a specific topic, are a crucial component to academia. They are especially important in the biomedical and health sciences, where they synthesize the state of medical evidence and conclude the best course of action for various diseases, pathologies, and treatments. Due to the immense amount of literature that exists, as well as the output rate of research, reviewing abstracts can be a laborious process. Automation may be able to significantly reduce this workload. Of course, such classifications are not easily automated due to the peculiar nature of written language. Machine learning may be able to help. This paper explored the viability and effectiveness of using machine learning modelling to classify abstracts according to specific exclusion/inclusion criteria, as would be done in the first stage of a systematic review. The specific task was performing the classification of deciding whether an abstract is a randomized control trial (RCT) or not, a very common classification made in systematic reviews in the healthcare field. Random training/testing splits of an n=2042 dataset of labelled abstracts were repeatedly created (1000 times in total), with a model trained and tested on each of these instances. A Bayes classifier as well as an SVM classifier were used, and compared to non-machine learning, simplistic approaches to textual classification. An SVM classifier was seen to be highly effective, yielding a 90% accuracy, as well as an F1 score of 0.84, and yielded a potential workload reduction of 70%. This shows that machine learning has the potential to significantly revolutionize the abstract screening process in healthcare systematic reviews.

In this work, we attempt to solve the Hit Song Science problem, which aims to predict which songs will become chart-topping hits. We constructed a dataset with approximately 1.8 million hit and non-hit songs and extracted their audio features using the Spotify Web API. We test four models on our dataset. Our best model was random forest, which was able to predict Billboard song success with 88% accuracy.

--Deep neural networks (DNNs) have demonstrated impressive performance on many challenging machine learning tasks. However, DNNs are vulnerable to adversarial inputs generated by adding maliciously crafted perturbations to the benign inputs. As a growing number of attacks have been reported to generate adversarial inputs of varying sophistication, the defense-attack arms race has been accelerated. MODEF intelligently combines unsupervised model denoising ensemble with supervised model verification ensemble by quantifying model diversity, aiming to boost the robustness of the target model against adversarial examples. Evaluated using eleven representative attacks on popular benchmark datasets, we show that MODEF achieves remarkable defense success rates, compared with existing defense methods, and provides a superior capability of repairing adversarial inputs and making correct predictions with high accuracy in the presence of black-box attacks. The recent advances in deep neural networks (DNNs) have powered numerous applications in different domains due to their outstanding performance compared to traditional machine learning techniques. However, it has been shown that DNNs can be easily fooled by adversarial inputs [1], making them become a double-edged sword as the vulnerability of DNNs to adversarial attacks has posed serious threats to many security-critical applications, such as biometric authentication and autonomous driving. As a number of defenses are being proposed, more attacks of varying sophistication have been put forward, accelerating the defense-attack arms race. Some even argue that designing new attacks requires much less efforts than developing effective defenses. Thus, improving the robustness and defensibility against adversarial attacks is crucial. Adversarial examples are generated by maliciously perturbing benign examples sent to the target DNN model through querying its prediction API, aiming to fool and mislead the target model to misclassify by producing incorrect predictions randomly (untargeted attack) or purposefully (targeted attack).

In many real life situations, including job and loan applications, gatekeepers must make justified, real-time decisions about a person's fitness for a particular opportunity. People on both sides of such decisions have understandable concerns about their fairness, especially when they occur online or algorithmically. In this paper we consider the setting where we try to satisfy approximate fairness in an online decision making process where examples are sampled i.i.d from an underlying distribution. The fairness metric we consider is "equalized odds", which requires that approximately equalized false positive rates and false negative rates across groups. Our work follows from the classical learning from experts scheme and extends the multiplicative weights algorithm by maintaining an estimation for label distribution and keeping separate weights for label classes as well as groups. Our theoretical results show that approximate equalized odds can be achieved without sacrificing much regret from some distributions. We also demonstrate the algorithm on real data sets commonly used by the fairness community.