In many applications, it is of interest to assess the relative contribution of features (or subsets of features) toward the goal of predicting a response -- in other words, to gauge the variable importance of features. Most recent work on variable importance assessment has focused on describing the importance of features within the confines of a given prediction algorithm. However, such assessment does not necessarily characterize the prediction potential of features, and may provide a misleading reflection of the intrinsic value of these features. To address this limitation, we propose a general framework for nonparametric inference on interpretable algorithm-agnostic variable importance. We define variable importance as a population-level contrast between the oracle predictiveness of all available features versus all features except those under consideration. We propose a nonparametric efficient estimation procedure that allows the construction of valid confidence intervals, even when machine learning techniques are used. We also outline a valid strategy for testing the null importance hypothesis. Through simulations, we show that our proposal has good operating characteristics, and we illustrate its use with data from a study of an antibody against HIV-1 infection.

Many machine learning systems today are trained on large amounts of human-annotated data. Data annotation tasks that require a high level of competency make data acquisition expensive, while the resulting labels are often subjective, inconsistent, and may contain a variety of human biases. To improve the data quality, practitioners often need to collect multiple annotations per example and aggregate them before training models. Such a multi-stage approach results in redundant annotations and may often produce imperfect "ground truth" that may limit the potential of training accurate machine learning models. We propose a new end-to-end framework that enables us to: (i) merge the aggregation step with model training, thus allowing deep learning systems to learn to predict ground truth estimates directly from the available data, and (ii) model difficulties of examples and learn representations of the annotators that allow us to estimate and take into account their competencies. Our approach is general and has many applications, including training more accurate models on crowdsourced data, ensemble learning, as well as classifier accuracy estimation from unlabeled data. We conduct an extensive experimental evaluation of our method on 5 crowdsourcing datasets of varied difficulty and show accuracy gains of up to 25% over the current state-of-the-art approaches for aggregating annotations, as well as significant reductions in the required annotation redundancy.

Inability to test at scale has become Achille's heel in humanity's ongoing war against COVID-19 pandemic. An agile, scalable and cost-effective testing, deployable at a global scale, can act as a game changer in this war. To address this challenge, building on the promising results of our prior work on cough-based diagnosis of a motley of respiratory diseases, we develop an Artificial Intelligence (AI)-based test for COVID-19 preliminary diagnosis. The test is deployable at scale through a mobile app named AI4COVID-19. The AI4COVID-19 app requires 2-second cough recordings of the subject. By analyzing the cough samples through an AI engine running in the cloud, the app returns a preliminary diagnosis within a minute. Unfortunately, cough is common symptom of over two dozen non-COVID-19 related medical conditions. This makes the COVID-19 diagnosis from cough alone an extremely challenging problem. We solve this problem by developing a novel multi-pronged mediator centered risk-averse AI architecture that minimizes misdiagnosis. At the time of writing, our AI engine can distinguish between COVID-19 patient coughs and several types of non-COVID-19 coughs with over 90% accuracy. AI4COVID-19's performance is likely to improve as more and better data becomes available. This paper presents a proof of concept to encourage controlled clinical trials and serves as a call for labeled cough data. AI4COVID-19 is not designed to compete with clinical testing. Instead, it offers a complementing tele-testing tool deployable anytime, anywhere, by anyone, so clinical-testing and treatment can be channeled to those who need it the most, thereby saving more lives.

The information ecosystem today is overwhelmed by an unprecedented quantity of data on versatile topics are with varied quality. However, the quality of information disseminated in the field of medicine has been questioned as the negative health consequences of health misinformation can be life-threatening. There is currently no generic automated tool for evaluating the quality of online health information spanned over a broad range. To address this gap, in this paper, we applied a data mining approach to automatically assess the quality of online health articles based on 10 quality criteria. We have prepared a labeled dataset with 53012 features and applied different feature selection methods to identify the best feature subset with which our trained classifier achieved an accuracy of 84%-90% varied over 10 criteria. Our semantic analysis of features shows the underpinning associations between the selected features & assessment criteria and further rationalize our assessment approach. Our findings will help in identifying high-quality health articles and thus aiding users in shaping their opinion to make the right choice while picking health-related help from online.

Random Forest remains one of Data Mining's most enduring ensemble algorithms, achieving well-documented levels of accuracy and processing speed, as well as regularly appearing in new research. However, with data mining now reaching the domain of hardware-constrained devices such as smartphones and Internet of Things (IoT) devices, there is continued need for further research into algorithm efficiency to deliver greater processing speed without sacrificing accuracy. Our proposed FastForest algorithm delivers an average 24% increase in processing speed compared with Random Forest whilst maintaining (and frequently exceeding) it on classification accuracy over tests involving 45 datasets. FastForest achieves this result through a combination of three optimising components - Subsample Aggregating ('Subbagging'), Logarithmic Split-Point Sampling and Dynamic Restricted Subspacing. Moreover, detailed testing of Subbagging sizes has found an optimal scalar delivering a positive mix of processing performance and accuracy.

Applications based on Machine Learning models have now become an indispensable part of the everyday life and the professional world. A critical question then recently arised among the population: Do algorithmic decisions convey any type of discrimination against specific groups of population or minorities? In this paper, we show the importance of understanding how a bias can be introduced into automatic decisions. We first present a mathematical framework for the fair learning problem, specifically in the binary classification setting. We then propose to quantify the presence of bias by using the standard Disparate Impact index on the real and well-known Adult income data set. Finally, we check the performance of different approaches aiming to reduce the bias in binary classification outcomes. Importantly, we show that some intuitive methods are ineffective. This sheds light on the fact trying to make fair machine learning models may be a particularly challenging task, in particular when the training observations contain a bias.

Several studies point out different causes of performance degradation in supervised machine learning. Problems such as class imbalance, overlapping, small-disjuncts, noisy labels, and sparseness limit accuracy in classification algorithms. Even though a number of approaches either in the form of a methodology or an algorithm try to minimize performance degradation, they have been isolated efforts with limited scope. Most of these approaches focus on remediation of one among many problems, with experimental results coming from few datasets and classification algorithms, insufficient measures of prediction power, and lack of statistical validation for testing the real benefit of the proposed approach. This paper consists of two main parts: In the first part, a novel probabilistic diagnostic model based on identifying signs and symptoms of each problem is presented. Thereby, early and correct diagnosis of these problems is to be achieved in order to select not only the most convenient remediation treatment but also unbiased performance metrics. Secondly, the behavior and performance of several supervised algorithms are studied when training sets have such problems. Therefore, prediction of success for treatments can be estimated across classifiers.

In this paper, we propose FairNN a neural network that performs joint feature representation and classification for fairness-aware learning. Our approach optimizes a multi-objective loss function in which (a) learns a fair representation by suppressing protected attributes (b) maintains the information content by minimizing a reconstruction loss and (c) allows for solving a classification task in a fair manner by minimizing the classification error and respecting the equalized odds-based fairness regularizer. Our experiments on a variety of datasets demonstrate that such a joint approach is superior to separate treatment of unfairness in representation learning or supervised learning. Additionally, our regularizers can be adaptively weighted to balance the different components of the loss function, thus allowing for a very general framework for conjoint fair representation learning and decision making.

Detecting anomalous inputs is critical for safely deploying deep learning models in the real world. Existing approaches for detecting out-of-distribution (OOD) examples work well when evaluated on natural samples drawn from a sufficiently different distribution than the training data distribution. However, in this paper, we show that existing detection mechanisms can be extremely brittle when evaluating on inputs with minimal adversarial perturbations which don't change their semantics. Formally, we introduce a novel and challenging problem, Robust Out-of-Distribution Detection, and propose an algorithm that can fool existing OOD detectors by adding small perturbations to the inputs while preserving their semantics and thus the distributional membership. We take a first step to solve this challenge, and propose an effective algorithm called ALOE, which performs robust training by exposing the model to both adversarially crafted inlier and outlier examples. Our method can be flexibly combined with, and render existing methods robust. On common benchmark datasets, we show that ALOE substantially improves the robustness of state-of-the-art OOD detection, with 58.4% AUROC improvement on CIFAR-10 and 46.59% improvement on CIFAR-100. Finally, we provide theoretical analysis for our method, underpinning the empirical results above.

Social biases based on gender, race, etc. have been shown to pollute machine learning (ML) pipeline predominantly via biased training datasets. Crowdsourcing, a popular cost-effective measure to gather labeled training datasets, is not immune to the inherent social biases of crowd workers. To ensure such social biases aren't passed onto the curated datasets, it's important to know how biased each crowd worker is. In this work, we propose a new method based on counterfactual fairness to quantify the degree of inherent social bias in each crowd worker. This extra information can be leveraged together with individual worker responses to curate a less biased dataset.