Learning to detect real-world anomalous events through videolevel labels is a challenging task due to the rare occurrence of anomalies as well as noise in the labels. In this work, we propose a weakly supervised anomaly detection method which has manifold contributions including 1) a random batch based training procedure to reduce inter-batch correlation, 2) a normalcy suppression mechanism to minimize anomaly scores of the normal regions of a video by taking into account the overall information available in one training batch, and 3) a clustering distance based loss to contribute towards mitigating the label noise and to produce better anomaly representations by encouraging our model to generate distinct normal and anomalous clusters. The proposed method obtains 83.03% and 89.67% frame-level AUC performance on the UCF-Crime and ShanghaiTech datasets respectively, demonstrating its superiority over the existing state-of-the-art algorithms.

Pain in sickle cell disease (SCD) is often associated with increased morbidity, mortality, and high healthcare costs. The standard method for predicting the absence, presence, and intensity of pain has long been self-report. However, medical providers struggle to manage patients based on subjective pain reports correctly and pain medications often lead to further difficulties in patient communication as they may cause sedation and sleepiness. Recent studies have shown that objective physiological measures can predict subjective self-reported pain scores for inpatient visits using machine learning (ML) techniques. In this study, we evaluate the generalizability of ML techniques to data collected from 50 patients over an extended period across three types of hospital visits (i.e., inpatient, outpatient and outpatient evaluation). We compare five classification algorithms for various pain intensity levels at both intra-individual (within each patient) and inter-individual (between patients) level. While all the tested classifiers perform much better than chance, a Decision Tree (DT) model performs best at predicting pain on an 11-point severity scale (from 0-10) with an accuracy of 0.728 at an inter-individual level and 0.653 at an intra-individual level. The accuracy of DT significantly improves to 0.941 on a 2-point rating scale (i.e., no/mild pain: 0-5, severe pain: 6-10) at an intra-individual level. Our experimental results demonstrate that ML techniques can provide an objective and quantitative evaluation of pain intensity levels for all three types of hospital visits.

Pull requests are a key part of the collaborative software development and code review process today. However, pull requests can also slow down the software development process when the reviewer(s) or the author do not actively engage with the pull request. In this work, we design an end-to-end service, Nudge, for accelerating overdue pull requests towards completion by reminding the author or the reviewer(s) to engage with their overdue pull requests. First, we use models based on effort estimation and machine learning to predict the completion time for a given pull request. Second, we use activity detection to reduce false positives. Lastly, we use dependency determination to understand the blocker of the pull request and nudge the appropriate actor(author or reviewer(s)). We also do a correlation analysis to understand the statistical relationship between the pull request completion times and various pull request and developer related attributes. Nudge has been deployed on 147 repositories at Microsoft since 2019. We do a large scale evaluation based on the implicit and explicit feedback we received from sending the Nudge notifications on 8,500 pull requests. We observe significant reduction in completion time, by over 60%, for pull requests which were nudged thus increasing the efficiency of the code review process and accelerating the pull request progression.

High-dimensional representations for words, text, images, knowledge graphs and other structured data are commonly used in different paradigms of machine learning and data mining. These representations have different degrees of interpretability, with efficient distributed representations coming at the cost of the loss of feature to dimension mapping. This implies that there is obfuscation in the way concepts are captured in these embedding spaces. Its effects are seen in many representations and tasks, one particularly problematic one being in language representations where the societal biases, learned from underlying data, are captured and occluded in unknown dimensions and subspaces. As a result, invalid associations (such as different races and their association with a polar notion of good versus bad) are made and propagated by the representations, leading to unfair outcomes in different tasks where they are used. This work addresses some of these problems pertaining to the transparency and interpretability of such representations. A primary focus is the detection, quantification, and mitigation of socially biased associations in language representation.

Early risk diagnosis and driving anomaly detection from vehicle stream are of great benefits in a range of advanced solutions towards Smart Road and crash prevention, although there are intrinsic challenges, especially lack of ground truth, definition of multiple risk exposures. This study proposes a domain-specific automatic clustering (termed Autocluster) to self-learn the optimal models for unsupervised risk assessment, which integrates key steps of risk clustering into an auto-optimisable pipeline, including feature and algorithm selection, hyperparameter auto-tuning. Firstly, based on surrogate conflict measures, indicator-guided feature extraction is conducted to construct temporal-spatial and kinematical risk features. Then we develop an elimination-based model reliance importance (EMRI) method to unsupervised-select the useful features. Secondly, we propose balanced Silhouette Index (bSI) to evaluate the internal quality of imbalanced clustering. A loss function is designed that considers the clustering performance in terms of internal quality, inter-cluster variation, and model stability. Thirdly, based on Bayesian optimisation, the algorithm selection and hyperparameter auto-tuning are self-learned to generate the best clustering partitions. Various algorithms are comprehensively investigated. Herein, NGSIM vehicle trajectory data is used for test-bedding. Findings show that Autocluster is reliable and promising to diagnose multiple distinct risk exposures inherent to generalised driving behaviour. Besides, we also delve into risk clustering, such as, algorithms heterogeneity, Silhouette analysis, hierarchical clustering flows, etc. Meanwhile, the Autocluster is also a method for unsupervised multi-risk data labelling and indicator threshold calibration. Furthermore, Autocluster is useful to tackle the challenges in imbalanced clustering without ground truth or priori knowledge

In the last few decades, building regression models for non-scalar variables, including time series, text, image, and video, has attracted increasing interests of researchers from the data analytic community. In this paper, we focus on a multivariate time series regression problem. Specifically, we aim to learn mathematical mappings from multiple chronologically measured numerical variables within a certain time interval S to multiple numerical variables of interest over time interval T. Prior arts, including the multivariate regression model, the Seq2Seq model, and the functional linear models, suffer from several limitations. The first two types of models can only handle regularly observed time series. Besides, the conventional multivariate regression models tend to be biased and inefficient, as they are incapable of encoding the temporal dependencies among observations from the same time series. The sequential learning models explicitly use the same set of parameters along time, which has negative impacts on accuracy. The function-on-function linear model in functional data analysis (a branch of statistics) is insufficient to capture complex correlations among the considered time series and suffer from underfitting easily. In this paper, we propose a general functional mapping that embraces the function-on-function linear model as a special case. We then propose a non-linear function-on-function model using the fully connected neural network to learn the mapping from data, which addresses the aforementioned concerns in the existing approaches. For the proposed model, we describe in detail the corresponding numerical implementation procedures. The effectiveness of the proposed model is demonstrated through the application to two real-world problems.

This work considers the problem of fitting functional models with sparsely and irregularly sampled functional data. It overcomes the limitations of the state-of-the-art methods, which face major challenges in the fitting of more complex non-linear models. Currently, many of these models cannot be consistently estimated unless the number of observed points per curve grows sufficiently quickly with the sample size, whereas, we show numerically that a modified approach with more modern multiple imputation methods can produce better estimates in general. We also propose a new imputation approach that combines the ideas of {\it MissForest} with {\it Local Linear Forest} and compare their performance with {\it PACE} and several other multivariate multiple imputation methods. This work is motivated by a longitudinal study on smoking cessation, in which the Electronic Health Records (EHR) from Penn State PaTH to Health allow for the collection of a great deal of data, with highly variable sampling. To illustrate our approach, we explore the relation between relapse and diastolic blood pressure. We also consider a variety of simulation schemes with varying levels of sparsity to validate our methods.

The estimation of shortest paths and intrinsic distances on surfaces is a fundamental problem in computational geometry with wide-ranging applications. In motion planning, shortest paths represent resource-efficient sequences of actions to be undertaken by the agent in some given configuration space [57, 56]. In addition to the clear applications to robot locomotion and manipulation, this framework has bore fruit in the field of biology wherein proteins and folding networks are of great interest [2, 76]. In cluster analysis, geodesic distances have found use as a similarity metric to create partitions that respect the underlying geometry [51, 65, 58]. In manifold learning, the Isometric Feature Mapping (Isomap) algorithm crucially depends on the approximation of geodesic distances on the underlying surface [75], and so does another important algorithm, Maximum Variance Unfolding (MVU) [79] although in disguise [64, 12]. This is closely related to the estimation of distances for the purpose of embedding a (weighted) graph (aka multidimensional scaling with missing distances), with one of the first methods suggested for that purpose being that of using the graph distances [55, 71, 70, 62].

The Expectation Maximization (EM) algorithm is a key reference for inference in latent variable models; unfortunately, its computational cost is prohibitive in the large scale learning setting. In this paper, we propose an extension of the Stochastic Path-Integrated Differential EstimatoR EM (SPIDER-EM) and derive complexity bounds for this novel algorithm, designed to solve smooth nonconvex finite-sum optimization problems. We show that it reaches the same state of the art complexity bounds as SPIDER-EM; and provide conditions for a linear rate of convergence. Numerical results support our findings.

The defining challenge for causal inference from observational data is the presence of `confounders', covariates that affect both treatment assignment and the outcome. To address this challenge, practitioners collect and adjust for the covariates, hoping that they adequately correct for confounding. However, including every observed covariate in the adjustment runs the risk of including `bad controls', variables that \emph{induce} bias when they are conditioned on. The problem is that we do not always know which variables in the covariate set are safe to adjust for and which are not. To address this problem, we develop Nearly Invariant Causal Estimation (NICE). NICE uses invariant risk minimization (IRM) [Arj19] to learn a representation of the covariates that, under some assumptions, strips out bad controls but preserves sufficient information to adjust for confounding. Adjusting for the learned representation, rather than the covariates themselves, avoids the induced bias and provides valid causal inferences. NICE is appropriate in the following setting. i) We observe data from multiple environments that share a common causal mechanism for the outcome, but that differ in other ways. ii) In each environment, the collected covariates are a superset of the causal parents of the outcome, and contain sufficient information for causal identification. iii) But the covariates also may contain bad controls, and it is unknown which covariates are safe to adjust for and which ones induce bias. We evaluate NICE on both synthetic and semi-synthetic data. When the covariates contain unknown collider variables and other bad controls, NICE performs better than existing methods that adjust for all the covariates.