Classifiers are among the most widely used supervised machine learning algorithms. Many classification models exist, and choosing the right one for a given task is difficult. During model selection and debugging, data scientists need to asses classifier performance, evaluate the training behavior over time, and compare different models. Typically, this analysis is based on single-number performance measures such as accuracy. A more detailed evaluation of classifiers is possible by inspecting class errors. The confusion matrix is an established way for visualizing these class errors, but it was not designed with temporal or comparative analysis in mind. More generally, established performance analysis systems do not allow a combined temporal and comparative analysis of class-level information. To address this issue, we propose ConfusionFlow, an interactive, comparative visualization tool that combines the benefits of class confusion matrices with the visualization of performance characteristics over time. ConfusionFlow is model-agnostic and can be used to compare performances for different model types, model architectures, and/or training and test datasets. We demonstrate the usefulness of ConfusionFlow in the context of two practical problems: an analysis of the influence of network pruning on model errors, and a case study on instance selection strategies in active learning.

Predictive modeling is where machine learning finally comes into your data science project. I use the term predictive modeling because I think a good project is not one that just trains a model and obsesses over the accuracy, but also uses comprehensive statistical methods and tests to ensure that the outcomes from the model actually make sense and are significant. Based on the questions you asked in the business understanding stage, this is where you decide which model to pick for your problem. This is never an easy decision, and there is no single right answer. The model (or models, and you should always be testing several) that you end up training will be dependent on the size, type and quality of your data, how much time and computational resources you are willing to invest, and the type of output you intend to derive. There are a couple of different cheat sheets available online which have a flowchart that helps you decide the right algorithm based on the type of classification or regression problem you are trying to solve.

This paper deals with multivariate regression chain graphs (MVR CGs), which were introduced by Cox and Wermuth [3,4] to represent linear causal models with correlated errors. We consider the PC-like algorithm for structure learning of MVR CGs, which is a constraint-based method proposed by Sonntag and Pe\~{n}a in [18]. We show that the PC-like algorithm is order-dependent, in the sense that the output can depend on the order in which the variables are given. This order-dependence is a minor issue in low-dimensional settings. However, it can be very pronounced in high-dimensional settings, where it can lead to highly variable results. We propose two modifications of the PC-like algorithm that remove part or all of this order-dependence. Simulations under a variety of settings demonstrate the competitive performance of our algorithms in comparison with the original PC-like algorithm in low-dimensional settings and improved performance in high-dimensional settings.

Deep neural network (DNN) has demonstrated its success in multiple domains. However, DNN models are inherently vulnerable to adversarial examples, which are generated by adding adversarial perturbations to benign inputs to fool the DNN model to misclassify. In this paper, we present a cross-layer strategic ensemble framework and a suite of robust defense algorithms, which are attack-independent, and capable of auto-repairing and auto-verifying the target model being attacked. Our strategic ensemble approach makes three original contributions. First, we employ input-transformation diversity to design the input-layer strategic transformation ensemble algorithms. Second, we utilize model-disagreement diversity to develop the output-layer strategic model ensemble algorithms. Finally, we create an input-output cross-layer strategic ensemble defense that strengthens the defensibility by combining diverse input transformation based model ensembles with diverse output verification model ensembles. Evaluated over 10 attacks on ImageNet dataset, we show that our strategic ensemble defense algorithms can achieve high defense success rates and are more robust with high attack prevention success rates and low benign false negative rates, compared to existing representative defense methods.

Increasingly large electronic health records (EHRs) provide an opportunity to algorithmically learn medical knowledge. In one prominent example, a causal health knowledge graph could learn relationships between diseases and symptoms and then serve as a diagnostic tool to be refined with additional clinical input. Prior research has demonstrated the ability to construct such a graph from over 270,000 emergency department patient visits. In this work, we describe methods to evaluate a health knowledge graph for robustness. Moving beyond precision and recall, we analyze for which diseases and for which patients the graph is most accurate. We identify sample size and unmeasured confounders as major sources of error in the health knowledge graph. We introduce a method to leverage non-linear functions in building the causal graph to better understand existing model assumptions. Finally, to assess model generalizability, we extend to a larger set of complete patient visits within a hospital system. We conclude with a discussion on how to robustly extract medical knowledge from EHRs.

Cardiotoxicity related to cancer therapies has become a serious issue, diminishing cancer treatment outcomes and quality of life. Early detection of cancer patients at risk for cardiotoxicity before cardiotoxic treatments and providing preventive measures are potential solutions to improve cancer patients's quality of life. This study focuses on predicting the development of heart failure in cancer patients after cancer diagnoses using historical electronic health record (EHR) data. We examined four machine learning algorithms using 143,199 cancer patients from the University of Florida Health (UF Health) Integrated Data Repository (IDR). We identified a total number of 1,958 qualified cases and matched them to 15,488 controls by gender, age, race, and major cancer type. Two feature encoding strategies were compared to encode variables as machine learning features. The gradient boosting (GB) based model achieved the best AUC score of 0.9077 (with a sensitivity of 0.8520 and a specificity of 0.8138), outperforming other machine learning methods. We also looked into the subgroup of cancer patients with exposure to chemotherapy drugs and observed a lower specificity score (0.7089). The experimental results show that machine learning methods are able to capture clinical factors that are known to be associated with heart failure and that it is feasible to use machine learning methods to identify cancer patients at risk for cancer therapy-related heart failure.

In many review classification applications, a fine-grained analysis of the reviews is desirable, because different segments (e.g., sentences) of a review may focus on different aspects of the entity in question. However, training supervised models for segment-level classification requires segment labels, which may be more difficult or expensive to obtain than review labels. In this paper, we employ Multiple Instance Learning (MIL) and use only weak supervision in the form of a single label per review. First, we show that when inappropriate MIL aggregation functions are used, then MIL-based networks are outperformed by simpler baselines. Second, we propose a new aggregation function based on the sigmoid attention mechanism and show that our proposed model outperforms the state-of-the-art models for segment-level sentiment classification (by up to 9.8% in F1). Finally, we highlight the importance of fine-grained predictions in an important public-health application: finding actionable reports of foodborne illness. We show that our model achieves 48.6% higher recall compared to previous models, thus increasing the chance of identifying previously unknown foodborne outbreaks.

Nowadays processing of Big Security Data, such as log messages, is commonly used for intrusion detection purposed. Its heterogeneous nature, as well as combination of numerical and categorical attributes does not allow to apply the existing data mining methods directly on the data without feature preprocessing. Therefore, a rather computationally expensive conversion of categorical attributes into vector space should be utilised for analysis of such data. However, a well-known k-modes algorithm allows to cluster the categorical data directly and avoid conversion into the vector space. The existing implementations of k-modes for Big Data processing are ensemble-based and utilise two-step clustering, where data subsets are first clustered independently, whereas the resulting cluster modes are clustered again in order to calculate metamodes valid for all data subsets. In this paper, the novel frequency-based distance function is proposed for the second step of ensemble-based k-modes clustering. Besides this, the existing feature discretisation method from the previous work is utilised in order to adapt k-modes for processing of mixed data sets. The resulting k-metamodes algorithm was tested on two public security data sets and reached higher effectiveness in comparison with the previous work.

We consider the problem of automatically generating textual paraphrases with modified attributes or properties, focusing on the setting without parallel data (Hu et al., 2017; Shen et al., 2017). This setting poses challenges for evaluation. We show that the metric of post-transfer classification accuracy is insufficient on its own, and propose additional metrics based on semantic preservation and fluency as well as a way to combine them into a single overall score. We contribute new loss functions and training strategies to address the different metrics. Semantic preservation is addressed by adding a cyclic consistency loss and a loss based on paraphrase pairs, while fluency is improved by integrating losses based on style-specific language models. We experiment with a Yelp sentiment dataset and a new literature dataset that we propose, using multiple models that extend prior work (Shen et al., 2017). We demonstrate that our metrics correlate well with human judgments, at both the sentence-level and system-level. Automatic and manual evaluation also show large improvements over the baseline method of Shen et al. (2017). We hope that our proposed metrics can speed up system development for new textual transfer tasks while also encouraging the community to address our three complementary aspects of transfer quality.

Conventional inclusion criteria used in osteoarthritis clinical trials are not very effective in selecting patients who would benefit the most from a therapy under test. Typically these criteria select majority of patients who show no or limited disease progression during a short evaluation window of the study. As a consequence, less insight on the relative effect of the treatment can be gained from the collected data, and the efforts and resources invested in running the study are not paying off. This could be avoided, if selection criteria were more predictive of the future disease progression. In this article, we formulated the patient selection problem as a multi-class classification task, with classes based on clinically relevant measures of progression (over a time scale typical for clinical trials). Using data from two long-term knee osteoarthritis studies OAI and CHECK, we tested multiple algorithms and learning process configurations (including multi-classifier approaches, cost-sensitive learning, and feature selection), to identify the best performing machine learning models. We examined the behaviour of the best models, with respect to prediction errors and the impact of used features, to confirm their clinical relevance. We found that the model-based selection outperforms the conventional inclusion criteria, reducing by 20-25% the number of patients who show no progression and making the representation of the patient categories more even. This result indicates that our machine learning approach could lead to efficiency improvements in clinical trial design.