Kalyan Veeramachaneni

Sarah Alnegheimish, Dongyu Liu, Carles Sala et al. · mit

The detection of anomalies in time series data is a critical task with many monitoring applications. Existing systems often fail to encompass an end-to-end detection process, to facilitate comparative analysis of various anomaly detection methods, or to incorporate human knowledge to refine output. This precludes current methods from being used in real-world settings by practitioners who are not ML experts. In this paper, we introduce Sintel, a machine learning framework for end-to-end time series tasks such as anomaly detection. The framework uses state-of-the-art approaches to support all steps of the anomaly detection process. Sintel logs the entire anomaly detection journey, providing detailed documentation of anomalies over time. It enables users to analyze signals, compare methods, and investigate anomalies through an interactive visualization tool, where they can annotate, modify, create, and remove events. Using these annotations, the framework leverages human knowledge to improve the anomaly detection pipeline. We demonstrate the usability, efficiency, and effectiveness of Sintel through a series of experiments on three public time series datasets, as well as one real-world use case involving spacecraft experts tasked with anomaly analysis tasks. Sintel's framework, code, and datasets are open-sourced at https://github.com/sintel-dev/.

Lawrence Wong, Dongyu Liu, Laure Berti-Equille et al.

Anomaly detection on time series data is increasingly common across various industrial domains that monitor metrics in order to prevent potential accidents and economic losses. However, a scarcity of labeled data and ambiguous definitions of anomalies can complicate these efforts. Recent unsupervised machine learning methods have made remarkable progress in tackling this problem using either single-timestamp predictions or time series reconstructions. While traditionally considered separately, these methods are not mutually exclusive and can offer complementary perspectives on anomaly detection. This paper first highlights the successes and limitations of prediction-based and reconstruction-based methods with visualized time series signals and anomaly scores. We then propose AER (Auto-encoder with Regression), a joint model that combines a vanilla auto-encoder and an LSTM regressor to incorporate the successes and address the limitations of each method. Our model can produce bi-directional predictions while simultaneously reconstructing the original time series by optimizing a joint objective function. Furthermore, we propose several ways of combining the prediction and reconstruction errors through a series of ablation studies. Finally, we compare the performance of the AER architecture against two prediction-based methods and three reconstruction-based methods on 12 well-known univariate time series datasets from NASA, Yahoo, Numenta, and UCR. The results show that AER has the highest averaged F1 score across all datasets (a 23.5% improvement compared to ARIMA) while retaining a runtime similar to its vanilla auto-encoder and regressor components. Our model is available in Orion, an open-source benchmarking tool for time series anomaly detection.

Kevin Zhang, Neha Patki, Kalyan Veeramachaneni

The goal of this paper is to describe a system for generating synthetic sequential data within the Synthetic data vault. To achieve this, we present the Sequential model currently in SDV, an end-to-end framework that builds a generative model for multi-sequence, real-world data. This includes a novel neural network-based machine learning model, conditional probabilistic auto-regressive (CPAR) model. The overall system and the model is available in the open source Synthetic Data Vault (SDV) library {https://github.com/sdv-dev/SDV}, along with a variety of other models for different synthetic data needs. After building the Sequential SDV, we used it to generate synthetic data and compared its quality against an existing, non-sequential generative adversarial network based model called CTGAN. To compare the sequential synthetic data against its real counterpart, we invented a new metric called Multi-Sequence Aggregate Similarity (MSAS). We used it to conclude that our Sequential SDV model learns higher level patterns than non-sequential models without any trade-offs in synthetic data quality.

Sarah Alnegheimish, Laure Berti-Equille, Kalyan Veeramachaneni

Time series anomaly detection is a vital task in many domains, including patient monitoring in healthcare, forecasting in finance, and predictive maintenance in energy industries. This has led to a proliferation of anomaly detection methods, including deep learning-based methods. Benchmarks are essential for comparing the performances of these models as they emerge, in a fair, rigorous, and reproducible approach. Although several benchmarks for comparing models have been proposed, these usually rely on a one-time execution over a limited set of datasets, with comparisons restricted to a few models. We propose OrionBench: an end-user centric, continuously maintained benchmarking framework for unsupervised time series anomaly detection models. Our framework provides universal abstractions to represent models, hyperparameter standardization, extensibility to add new pipelines and datasets, pipeline verification, and frequent releases with published updates of the benchmark. We demonstrate how to use OrionBench, and the performance of pipelines across 17 releases published over the course of four years. We also walk through two real scenarios we experienced with OrionBench that highlight the importance of continuous benchmarking for unsupervised time series anomaly detection.

Alexandra Zytek, Sara Pido, Sarah Alnegheimish et al.

Explanations of machine learning (ML) model predictions generated by Explainable AI (XAI) techniques such as SHAP are essential for people using ML outputs for decision-making. We explore the potential of Large Language Models (LLMs) to transform these explanations into human-readable, narrative formats that align with natural communication. We address two key research questions: (1) Can LLMs reliably transform traditional explanations into high-quality narratives? and (2) How can we effectively evaluate the quality of narrative explanations? To answer these questions, we introduce Explingo, which consists of two LLM-based subsystems, a Narrator and Grader. The Narrator takes in ML explanations and transforms them into natural-language descriptions. The Grader scores these narratives on a set of metrics including accuracy, completeness, fluency, and conciseness. Our experiments demonstrate that LLMs can generate high-quality narratives that achieve high scores across all metrics, particularly when guided by a small number of human-labeled and bootstrapped examples. We also identified areas that remain challenging, in particular for effectively scoring narratives in complex domains. The findings from this work have been integrated into an open-source tool that makes narrative explanations available for further applications.

Lei Xu, Alfredo Cuesta-Infante, Laure Berti-Equille et al.

Adversarial examples are helpful for analyzing and improving the robustness of text classifiers. Generating high-quality adversarial examples is a challenging task as it requires generating fluent adversarial sentences that are semantically similar to the original sentences and preserve the original labels, while causing the classifier to misclassify them. Existing methods prioritize misclassification by maximizing each perturbation's effectiveness at misleading a text classifier; thus, the generated adversarial examples fall short in terms of fluency and similarity. In this paper, we propose a rewrite and rollback (R&R) framework for adversarial attack. It improves the quality of adversarial examples by optimizing a critique score which combines the fluency, similarity, and misclassification metrics. R&R generates high-quality adversarial examples by allowing exploration of perturbations that do not have immediate impact on the misclassification metric but can improve fluency and similarity metrics. We evaluate our method on 5 representative datasets and 3 classifier architectures. Our method outperforms current state-of-the-art in attack success rate by +16.2%, +12.8%, and +14.0% on the classifiers respectively. Code is available at https://github.com/DAI-Lab/fibber

Micah J. Smith, Jürgen Cito, Kelvin Lu et al.

While the open-source software development model has led to successful large-scale collaborations in building software systems, data science projects are frequently developed by individuals or small teams. We describe challenges to scaling data science collaborations and present a conceptual framework and ML programming model to address them. We instantiate these ideas in Ballet, a lightweight framework for collaborative, open-source data science through a focus on feature engineering, and an accompanying cloud-based development environment. Using our framework, collaborators incrementally propose feature definitions to a repository which are each subjected to an ML performance evaluation and can be automatically merged into an executable feature engineering pipeline. We leverage Ballet to conduct a case study analysis of an income prediction problem with 27 collaborators, and discuss implications for future designers of collaborative projects.

Sarah Alnegheimish, Najat Alrashed, Faisal Aleissa et al.

An estimated 180 papers focusing on deep learning and EHR were published between 2010 and 2018. Despite the common workflow structure appearing in these publications, no trusted and verified software framework exists, forcing researchers to arduously repeat previous work. In this paper, we propose Cardea, an extensible open-source automated machine learning framework encapsulating common prediction problems in the health domain and allows users to build predictive models with their own data. This system relies on two components: Fast Healthcare Interoperability Resources (FHIR) -- a standardized data structure for electronic health systems -- and several AUTOML frameworks for automated feature engineering, model selection, and tuning. We augment these components with an adaptive data assembler and comprehensive data- and model- auditing capabilities. We demonstrate our framework via 5 prediction tasks on MIMIC-III and Kaggle datasets, which highlight Cardea's human competitiveness, flexibility in problem definition, extensive feature generation capability, adaptable automatic data assembler, and its usability.

Alexander Geiger, Dongyu Liu, Sarah Alnegheimish et al.

Time series anomalies can offer information relevant to critical situations facing various fields, from finance and aerospace to the IT, security, and medical domains. However, detecting anomalies in time series data is particularly challenging due to the vague definition of anomalies and said data's frequent lack of labels and highly complex temporal correlations. Current state-of-the-art unsupervised machine learning methods for anomaly detection suffer from scalability and portability issues, and may have high false positive rates. In this paper, we propose TadGAN, an unsupervised anomaly detection approach built on Generative Adversarial Networks (GANs). To capture the temporal correlations of time series distributions, we use LSTM Recurrent Neural Networks as base models for Generators and Critics. TadGAN is trained with cycle consistency loss to allow for effective time-series data reconstruction. We further propose several novel methods to compute reconstruction errors, as well as different approaches to combine reconstruction errors and Critic outputs to compute anomaly scores. To demonstrate the performance and generalizability of our approach, we test several anomaly scoring techniques and report the best-suited one. We compare our approach to 8 baseline anomaly detection methods on 11 datasets from multiple reputable sources such as NASA, Yahoo, Numenta, Amazon, and Twitter. The results show that our approach can effectively detect anomalies and outperform baseline methods in most cases (6 out of 11). Notably, our method has the highest averaged F1 score across all the datasets. Our code is open source and is available as a benchmarking tool.

Kevin Alex Zhang, Alfredo Cuesta-Infante, Lei Xu et al.

Image steganography is a procedure for hiding messages inside pictures. While other techniques such as cryptography aim to prevent adversaries from reading the secret message, steganography aims to hide the presence of the message itself. In this paper, we propose a novel technique for hiding arbitrary binary data in images using generative adversarial networks which allow us to optimize the perceptual quality of the images produced by our model. We show that our approach achieves state-of-the-art payloads of 4.4 bits per pixel, evades detection by steganalysis tools, and is effective on images from multiple datasets. To enable fair comparisons, we have released an open source library that is available online at https://github.com/DAI-Lab/SteganoGAN.

Sarah Alnegheimish, Linh Nguyen, Laure Berti-Equille et al.

Recent studies have shown the ability of large language models to perform a variety of tasks, including time series forecasting. The flexible nature of these models allows them to be used for many applications. In this paper, we present a novel study of large language models used for the challenging task of time series anomaly detection. This problem entails two aspects novel for LLMs: the need for the model to identify part of the input sequence (or multiple parts) as anomalous; and the need for it to work with time series data rather than the traditional text input. We introduce sigllm, a framework for time series anomaly detection using large language models. Our framework includes a time-series-to-text conversion module, as well as end-to-end pipelines that prompt language models to perform time series anomaly detection. We investigate two paradigms for testing the abilities of large language models to perform the detection task. First, we present a prompt-based detection method that directly asks a language model to indicate which elements of the input are anomalies. Second, we leverage the forecasting capability of a large language model to guide the anomaly detection process. We evaluated our framework on 11 datasets spanning various sources and 10 pipelines. We show that the forecasting method significantly outperformed the prompting method in all 11 datasets with respect to the F1 score. Moreover, while large language models are capable of finding anomalies, state-of-the-art deep learning models are still superior in performance, achieving results 30% better than large language models.

Alexandra Zytek, Wei-En Wang, Dongyu Liu et al.

Users in many domains use machine learning (ML) predictions to help them make decisions. Effective ML-based decision-making often requires explanations of ML models and their predictions. While there are many algorithms that explain models, generating explanations in a format that is comprehensible and useful to decision-makers is a nontrivial task that can require extensive development overhead. We developed Pyreal, a highly extensible system with a corresponding Python implementation for generating a variety of interpretable ML explanations. Pyreal converts data and explanations between the feature spaces expected by the model, relevant explanation algorithms, and human users, allowing users to generate interpretable explanations in a low-code manner. Our studies demonstrate that Pyreal generates more useful explanations than existing systems while remaining both easy-to-use and efficient.

Michael Fuest, Alfredo Cuesta, Kalyan Veeramachaneni

Recent breakthroughs in large-scale generative modeling have demonstrated the potential of foundation models in domains such as natural language, computer vision, and protein structure prediction. However, their application in the energy and smart grid sector remains limited due to the scarcity and heterogeneity of high-quality data. In this work, we propose a method for creating high-fidelity electricity consumption time series data for rare and unseen context variables (e.g. location, building type, photovoltaics). Our approach, Context Encoding and Normalizing Time Series Generation, or CENTS, includes three key innovations: (i) A context normalization approach that enables inverse transformation for time series context variables unseen during training, (ii) a novel context encoder to condition any state-of-the-art time-series generator on arbitrary numbers and combinations of context variables, (iii) a framework for training this context encoder jointly with a time-series generator using an auxiliary context classification loss designed to increase expressivity of context embeddings and improve model performance. We further provide a comprehensive overview of different evaluation metrics for generative time series models. Our results highlight the efficacy of the proposed method in generating realistic household-level electricity consumption data, paving the way for training larger foundation models in the energy domain on synthetic as well as real-world data.

Alexandra Zytek, Sara Pidò, Kalyan Veeramachaneni

In response to the demand for Explainable Artificial Intelligence (XAI), we investigate the use of Large Language Models (LLMs) to transform ML explanations into natural, human-readable narratives. Rather than directly explaining ML models using LLMs, we focus on refining explanations computed using existing XAI algorithms. We outline several research directions, including defining evaluation metrics, prompt design, comparing LLM models, exploring further training methods, and integrating external data. Initial experiments and user study suggest that LLMs offer a promising way to enhance the interpretability and usability of XAI.

Lei Xu, Sarah Alnegheimish, Laure Berti-Equille et al.

In text classification, creating an adversarial example means subtly perturbing a few words in a sentence without changing its meaning, causing it to be misclassified by a classifier. A concerning observation is that a significant portion of adversarial examples generated by existing methods change only one word. This single-word perturbation vulnerability represents a significant weakness in classifiers, which malicious users can exploit to efficiently create a multitude of adversarial examples. This paper studies this problem and makes the following key contributions: (1) We introduce a novel metric $ρ$ to quantitatively assess a classifier's robustness against single-word perturbation. (2) We present the SP-Attack, designed to exploit the single-word perturbation vulnerability, achieving a higher attack success rate, better preserving sentence meaning, while reducing computation costs compared to state-of-the-art adversarial methods. (3) We propose SP-Defense, which aims to improve \r{ho} by applying data augmentation in learning. Experimental results on 4 datasets and BERT and distilBERT classifiers show that SP-Defense improves $ρ$ by 14.6% and 13.9% and decreases the attack success rate of SP-Attack by 30.4% and 21.2% on two classifiers respectively, and decreases the attack success rate of existing attack methods that involve multiple-word perturbations.

Alexandra Zytek, Wei-En Wang, Sofia Koukoura et al.

Through past experiences deploying what we call usable ML (one step beyond explainable ML, including both explanations and other augmenting information) to real-world domains, we have learned three key lessons. First, many organizations are beginning to hire people who we call ``bridges'' because they bridge the gap between ML developers and domain experts, and these people fill a valuable role in developing usable ML applications. Second, a configurable system that enables easily iterating on usable ML interfaces during collaborations with bridges is key. Finally, there is a need for continuous, in-deployment evaluations to quantify the real-world impact of usable ML. Throughout this paper, we apply these lessons to the task of wind turbine monitoring, an essential task in the renewable energy domain. Turbine engineers and data analysts must decide whether to perform costly in-person investigations on turbines to prevent potential cases of brakepad failure, and well-tuned usable ML interfaces can aid with this decision-making process. Through the applications of our lessons to this task, we hope to demonstrate the potential real-world impact of usable ML in the renewable energy domain.

Alexandra Zytek, Ignacio Arnaldo, Dongyu Liu et al.

Through extensive experience developing and explaining machine learning (ML) applications for real-world domains, we have learned that ML models are only as interpretable as their features. Even simple, highly interpretable model types such as regression models can be difficult or impossible to understand if they use uninterpretable features. Different users, especially those using ML models for decision-making in their domains, may require different levels and types of feature interpretability. Furthermore, based on our experiences, we claim that the term "interpretable feature" is not specific nor detailed enough to capture the full extent to which features impact the usefulness of ML explanations. In this paper, we motivate and discuss three key lessons: 1) more attention should be given to what we refer to as the interpretable feature space, or the state of features that are useful to domain experts taking real-world actions, 2) a formal taxonomy is needed of the feature properties that may be required by these domain experts (we propose a partial taxonomy in this paper), and 3) transforms that take data from the model-ready state to an interpretable form are just as essential as traditional ML transforms that prepare features for the model.

Dongyu Liu, Sarah Alnegheimish, Alexandra Zytek et al.

Detecting anomalies in time-varying multivariate data is crucial in various industries for the predictive maintenance of equipment. Numerous machine learning (ML) algorithms have been proposed to support automated anomaly identification. However, a significant amount of human knowledge is still required to interpret, analyze, and calibrate the results of automated analysis. This paper investigates current practices used to detect and investigate anomalies in time series data in industrial contexts and identifies corresponding needs. Through iterative design and working with nine experts from two industry domains (aerospace and energy), we characterize six design elements required for a successful visualization system that supports effective detection, investigation, and annotation of time series anomalies. We summarize an ideal human-AI collaboration workflow that streamlines the process and supports efficient and collaborative analysis. We introduce MTV (Multivariate Time Series Visualization), a visual analytics system to support such workflow. The system incorporates a set of novel visualization and interaction designs to support multi-faceted time series exploration, efficient in-situ anomaly annotation, and insight communication. Two user studies, one with 6 spacecraft experts (with routine anomaly analysis tasks) and one with 25 general end-users (without such tasks), are conducted to demonstrate the effectiveness and usefulness of MTV.

Furui Cheng, Dongyu Liu, Fan Du et al.

Machine learning (ML) is increasingly applied to Electronic Health Records (EHRs) to solve clinical prediction tasks. Although many ML models perform promisingly, issues with model transparency and interpretability limit their adoption in clinical practice. Directly using existing explainable ML techniques in clinical settings can be challenging. Through literature surveys and collaborations with six clinicians with an average of 17 years of clinical experience, we identified three key challenges, including clinicians' unfamiliarity with ML features, lack of contextual information, and the need for cohort-level evidence. Following an iterative design process, we further designed and developed VBridge, a visual analytics tool that seamlessly incorporates ML explanations into clinicians' decision-making workflow. The system includes a novel hierarchical display of contribution-based feature explanations and enriched interactions that connect the dots between ML features, explanations, and data. We demonstrated the effectiveness of VBridge through two case studies and expert interviews with four clinicians, showing that visually associating model explanations with patients' situational records can help clinicians better interpret and use model predictions when making clinician decisions. We further derived a list of design implications for developing future explainable ML tools to support clinical decision-making.

Micah J. Smith, Jürgen Cito, Kalyan Veeramachaneni

Developers in data science and other domains frequently use computational notebooks to create exploratory analyses and prototype models. However, they often struggle to incorporate existing software engineering tooling into these notebook-based workflows, leading to fragile development processes. We introduce Assemblé, a new development environment for collaborative data science projects, in which promising code fragments of data science pipelines can be contributed as pull requests to an upstream repository entirely from within JupyterLab, abstracting away low-level version control tool usage. We describe the design and implementation of Assemblé and report on a user study of 23 data scientists.

Dongyu Liu, Kalyan Veeramachaneni, Alexander Geiger et al.

Anomaly detection plays a key role in air quality analysis by enhancing situational awareness and alerting users to potential hazards. However, existing anomaly detection approaches for air quality analysis have their own limitations regarding parameter selection (e.g., need for extensive domain knowledge), computational expense, general applicability (e.g., require labeled data), interpretability, and the efficiency of analysis. Furthermore, the poor quality of collected air quality data (inconsistently formatted and sometimes missing) also increases the difficulty of analysis substantially. In this paper, we systematically formulate design requirements for a system that can solve these limitations and then propose AQEyes, an integrated visual analytics system for efficiently monitoring, detecting, and examining anomalies in air quality data. In particular, we propose a unified end-to-end tunable machine learning pipeline that includes several data pre-processors and featurizers to deal with data quality issues. The pipeline integrates an efficient unsupervised anomaly detection method that works without the use of labeled data and overcomes the limitations of existing approaches. Further, we develop an interactive visualization system to visualize the outputs from the pipeline. The system incorporates a set of novel visualization and interaction designs, allowing analysts to visually examine air quality dynamics and anomalous events in multiple scales and from multiple facets. We demonstrate the performance of this pipeline through a quantitative evaluation and show the effectiveness of the visualization system using qualitative case studies on real-world datasets.

Alexandra Zytek, Dongyu Liu, Rhema Vaithianathan et al.

Machine learning (ML) is being applied to a diverse and ever-growing set of domains. In many cases, domain experts - who often have no expertise in ML or data science - are asked to use ML predictions to make high-stakes decisions. Multiple ML usability challenges can appear as result, such as lack of user trust in the model, inability to reconcile human-ML disagreement, and ethical concerns about oversimplification of complex problems to a single algorithm output. In this paper, we investigate the ML usability challenges that present in the domain of child welfare screening through a series of collaborations with child welfare screeners. Following the iterative design process between the ML scientists, visualization researchers, and domain experts (child screeners), we first identified four key ML challenges and honed in on one promising explainable ML technique to address them (local factor contributions). Then we implemented and evaluated our visual analytics tool, Sibyl, to increase the interpretability and interactivity of local factor contributions. The effectiveness of our tool is demonstrated by two formal user studies with 12 non-expert participants and 13 expert participants respectively. Valuable feedback was collected, from which we composed a list of design implications as a useful guideline for researchers who aim to develop an interpretable and interactive visualization tool for ML prediction models deployed for child welfare screeners and other similar domain experts.

Lei Xu, Ivan Ramirez, Kalyan Veeramachaneni

Most adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters. Few try to attack classifiers by rewriting a whole sentence, due to the difficulties inherent in sentence-level rephrasing as well as the problem of setting the criteria for legitimate rewriting. In this paper, we explore the problem of creating adversarial examples with sentence-level rewriting. We design a new sampling method, named ParaphraseSampler, to efficiently rewrite the original sentence in multiple ways. Then we propose a new criteria for modification, called a sentence-level threaten model. This criteria allows for both word- and sentence-level changes, and can be adjusted independently in two dimensions: semantic similarity and grammatical quality. Experimental results show that many of these rewritten sentences are misclassified by the classifier. On all 6 datasets, our ParaphraseSampler achieves a better attack success rate than our baseline.

Shubhra Kanti Karmaker Santu, Md. Mahadi Hassan, Micah J. Smith et al.

As big data becomes ubiquitous across domains, and more and more stakeholders aspire to make the most of their data, demand for machine learning tools has spurred researchers to explore the possibilities of automated machine learning (AutoML). AutoML tools aim to make machine learning accessible for non-machine learning experts (domain experts), to improve the efficiency of machine learning, and to accelerate machine learning research. But although automation and efficiency are among AutoML's main selling points, the process still requires human involvement at a number of vital steps, including understanding the attributes of domain-specific data, defining prediction problems, creating a suitable training data set, and selecting a promising machine learning technique. These steps often require a prolonged back-and-forth that makes this process inefficient for domain experts and data scientists alike, and keeps so-called AutoML systems from being truly automatic. In this review article, we introduce a new classification system for AutoML systems, using a seven-tiered schematic to distinguish these systems based on their level of autonomy. We begin by describing what an end-to-end machine learning pipeline actually looks like, and which subtasks of the machine learning pipeline have been automated so far. We highlight those subtasks which are still done manually - generally by a data scientist - and explain how this limits domain experts' access to machine learning. Next, we introduce our novel level-based taxonomy for AutoML systems and define each level according to the scope of automation support provided. Finally, we lay out a roadmap for the future, pinpointing the research required to further automate the end-to-end machine learning pipeline and discussing important challenges that stand in the way of this ambitious goal.

Kevin Alex Zhang, Lei Xu, Alfredo Cuesta-Infante et al.

The goal of video watermarking is to embed a message within a video file in a way such that it minimally impacts the viewing experience but can be recovered even if the video is redistributed and modified, allowing media producers to assert ownership over their content. This paper presents RivaGAN, a novel architecture for robust video watermarking which features a custom attention-based mechanism for embedding arbitrary data as well as two independent adversarial networks which critique the video quality and optimize for robustness. Using this technique, we are able to achieve state-of-the-art results in deep learning-based video watermarking and produce watermarked videos which have minimal visual distortion and are robust against common video processing operations.

Yi Sun, Ivan Ramirez, Alfredo Cuesta-Infante et al.

In many real life situations, including job and loan applications, gatekeepers must make justified and fair real-time decisions about a person's fitness for a particular opportunity. In this paper, we aim to accomplish approximate group fairness in an online stochastic decision-making process, where the fairness metric we consider is equalized odds. Our work follows from the classical learning-from-experts scheme, assuming a finite set of classifiers (human experts, rules, options, etc) that cannot be modified. We run separate instances of the algorithm for each label class as well as sensitive groups, where the probability of choosing each instance is optimized for both fairness and regret. Our theoretical results show that approximately equalized odds can be achieved without sacrificing much regret. We also demonstrate the performance of the algorithm on real data sets commonly used by the fairness community.

Lei Xu, Maria Skoularidou, Alfredo Cuesta-Infante et al.

Modeling the probability distribution of rows in tabular data and generating realistic synthetic data is a non-trivial task. Tabular data usually contains a mix of discrete and continuous columns. Continuous columns may have multiple modes whereas discrete columns are sometimes imbalanced making the modeling difficult. Existing statistical and deep neural network models fail to properly model this type of data. We design TGAN, which uses a conditional generative adversarial network to address these challenges. To aid in a fair and thorough comparison, we design a benchmark with 7 simulated and 8 real datasets and several Bayesian network baselines. TGAN outperforms Bayesian methods on most of the real datasets whereas other deep learning methods could not.

Lei Xu, Shubhra Kanti Karmaker Santu, Kalyan Veeramachaneni

Most automation in machine learning focuses on model selection and hyper parameter tuning, and many overlook the challenge of automatically defining predictive tasks. We still heavily rely on human experts to define prediction tasks, and generate labels by aggregating raw data. In this paper, we tackle the challenge of defining useful prediction problems on event-driven time-series data. We introduce MLFriend to address this challenge. MLFriend first generates all possible prediction tasks under a predefined space, then interacts with a data scientist to learn the context of the data and recommend good prediction tasks from all the tasks in the space. We evaluate our system on three different datasets and generate a total of 2885 prediction tasks and solve them. Out of these 722 were deemed useful by expert data scientists. We also show that an automatic prediction task discovery system is able to identify top 10 tasks that a user may like within a batch of 100 tasks.

Micah J. Smith, Carles Sala, James Max Kanter et al.

As machine learning is applied more widely, data scientists often struggle to find or create end-to-end machine learning systems for specific tasks. The proliferation of libraries and frameworks and the complexity of the tasks have led to the emergence of "pipeline jungles" - brittle, ad hoc ML systems. To address these problems, we introduce the Machine Learning Bazaar, a new framework for developing machine learning and automated machine learning software systems. First, we introduce ML primitives, a unified API and specification for data processing and ML components from different software libraries. Next, we compose primitives into usable ML pipelines, abstracting away glue code, data flow, and data storage. We further pair these pipelines with a hierarchy of AutoML strategies - Bayesian optimization and bandit learning. We use these components to create a general-purpose, multi-task, end-to-end AutoML system that provides solutions to a variety of data modalities (image, text, graph, tabular, relational, etc.) and problem types (classification, regression, anomaly detection, graph matching, etc.). We demonstrate 5 real-world use cases and 2 case studies of our approach. Finally, we present an evaluation suite of 456 real-world ML tasks and describe the characteristics of 2.5 million pipelines searched over this task suite.

Qianwen Wang, Yao Ming, Zhihua Jin et al.

To relieve the pain of manually selecting machine learning algorithms and tuning hyperparameters, automated machine learning (AutoML) methods have been developed to automatically search for good models. Due to the huge model search space, it is impossible to try all models. Users tend to distrust automatic results and increase the search budget as much as they can, thereby undermining the efficiency of AutoML. To address these issues, we design and implement ATMSeer, an interactive visualization tool that supports users in refining the search space of AutoML and analyzing the results. To guide the design of ATMSeer, we derive a workflow of using AutoML based on interviews with machine learning experts. A multi-granularity visualization is proposed to enable users to monitor the AutoML process, analyze the searched models, and refine the search space in real time. We demonstrate the utility and usability of ATMSeer through two case studies, expert interviews, and a user study with 13 end users.

Yi Sun, Alfredo Cuesta-Infante, Kalyan Veeramachaneni

A vine copula model is a flexible high-dimensional dependence model which uses only bivariate building blocks. However, the number of possible configurations of a vine copula grows exponentially as the number of variables increases, making model selection a major challenge in development. In this work, we formulate a vine structure learning problem with both vector and reinforcement learning representation. We use neural network to find the embeddings for the best possible vine model and generate a structure. Throughout experiments on synthetic and real-world datasets, we show that our proposed approach fits the data better in terms of log-likelihood. Moreover, we demonstrate that the model is able to generate high-quality samples in a variety of applications, making it a good candidate for synthetic data generation.

Gaurav Sheni, Benjamin Schreck, Roy Wedge et al.

In this paper, we present a data science automation system called Prediction Factory. The system uses several key automation algorithms to enable data scientists to rapidly develop predictive models and share them with domain experts. To assess the system's impact, we implemented 3 different interfaces for creating predictive modeling projects: baseline automation, full automation, and optional automation. With a dataset of online grocery shopper behaviors, we divided data scientists among the interfaces to specify prediction problems, learn and evaluate models, and write a report for domain experts to judge whether or not to fund to continue working on. In total, 22 data scientists created 94 reports that were judged 296 times by 26 experts. In a head-to-head trial, reports generated utilizing full data science automation interface reports were funded 57.5% of the time, while the ones that used baseline automation were only funded 42.5% of the time. An intermediate interface which supports optional automation generated reports were funded 58.6% more often compared to the baseline. Full automation and optional automation reports were funded about equally when put head-to-head. These results demonstrate that Prediction Factory has implemented a critical amount of automation to augment the role of data scientists and improve business outcomes.

Lei Xu, Kalyan Veeramachaneni

Generative adversarial networks (GANs) implicitly learn the probability distribution of a dataset and can draw samples from the distribution. This paper presents, Tabular GAN (TGAN), a generative adversarial network which can generate tabular data like medical or educational records. Using the power of deep neural networks, TGAN generates high-quality and fully synthetic tables while simultaneously generating discrete and continuous variables. When we evaluate our model on three datasets, we find that TGAN outperforms conventional statistical generative models in both capturing the correlation between columns and scaling up for large datasets.

James Max Kanter, Benjamin Schreck, Kalyan Veeramachaneni

ML 2.0: In this paper, we propose a paradigm shift from the current practice of creating machine learning models - which requires months-long discovery, exploration and "feasibility report" generation, followed by re-engineering for deployment - in favor of a rapid, 8-week process of development, understanding, validation and deployment that can executed by developers or subject matter experts (non-ML experts) using reusable APIs. This accomplishes what we call a "minimum viable data-driven model," delivering a ready-to-use machine learning model for problems that haven't been solved before using machine learning. We provide provisions for the refinement and adaptation of the "model," with strict enforcement and adherence to both the scaffolding/abstractions and the process. We imagine that this will bring forth the second phase in machine learning, in which discovery is subsumed by more targeted goals of delivery and impact.

Roy Wedge, James Max Kanter, Santiago Moral Rubio et al.

In this paper, we present an automated feature engineering based approach to dramatically reduce false positives in fraud prediction. False positives plague the fraud prediction industry. It is estimated that only 1 in 5 declared as fraud are actually fraud and roughly 1 in every 6 customers have had a valid transaction declined in the past year. To address this problem, we use the Deep Feature Synthesis algorithm to automatically derive behavioral features based on the historical data of the card associated with a transaction. We generate 237 features (>100 behavioral patterns) for each transaction, and use a random forest to learn a classifier. We tested our machine learning model on data from a large multinational bank and compared it to their existing solution. On an unseen data of 1.852 million transactions, we were able to reduce the false positives by 54% and provide a savings of 190K euros. We also assess how to deploy this solution, and whether it necessitates streaming computation for real time scoring. We found that our solution can maintain similar benefits even when historical features are computed once every 7 days.

Colin Taylor, Kalyan Veeramachaneni, Una-May O'Reilly

Understanding why students stopout will help in understanding how students learn in MOOCs. In this report, part of a 3 unit compendium, we describe how we build accurate predictive models of MOOC student stopout. We document a scalable, stopout prediction methodology, end to end, from raw source data to model analysis. We attempted to predict stopout for the Fall 2012 offering of 6.002x. This involved the meticulous and crowd-sourced engineering of over 25 predictive features extracted for thousands of students, the creation of temporal and non-temporal data representations for use in predictive modeling, the derivation of over 10 thousand models with a variety of state-of-the-art machine learning techniques and the analysis of feature importance by examining over 70000 models. We found that stop out prediction is a tractable problem. Our models achieved an AUC (receiver operating characteristic area-under-the-curve) as high as 0.95 (and generally 0.88) when predicting one week in advance. Even with more difficult prediction problems, such as predicting stop out at the end of the course with only one weeks' data, the models attained AUCs of 0.7.

Kalyan Veeramachaneni, Sherif Halawa, Franck Dernoncourt et al.

We present a shared data model for enabling data science in Massive Open Online Courses (MOOCs). The model captures students interactions with the online platform. The data model is platform agnostic and is based on some basic core actions that students take on an online learning platform. Students usually interact with the platform in four different modes: Observing, Submitting, Collaborating and giving feedback. In observing mode students are simply browsing the online platform, watching videos, reading material, reading book or watching forums. In submitting mode, students submit information to the platform. This includes submissions towards quizzes, homeworks, or any assessment modules. In collaborating mode students interact with other students or instructors on forums, collaboratively editing wiki or chatting on google hangout or other hangout venues. With this basic definitions of activities, and a data model to store events pertaining to these activities, we then create a common terminology to map Coursera and edX data into this shared data model. This shared data model called MOOCdb becomes the foundation for a number of collaborative frameworks that enable progress in data science without the need to share the data.