Deep learning techniques have advanced rapidly in recent years, leading to significant progress in pre-trained and fine-tuned large-scale AI models. For example, in the natural language processing domain, the traditional "pre-train, fine-tune" paradigm is shifting towards the "pre-train, prompt, and predict" paradigm, which has achieved great success on many tasks across different application domains such as ChatGPT/BARD for Conversational AI and P5 for a unified recommendation system. Moreover, there has been a growing interest in models that combine vision and language modalities (vision-language models) which are applied to tasks like Visual Captioning/Generation. Considering the recent technological revolution, it is essential to emphasize these paradigm shifts and highlight the paradigms with the potential to solve different tasks. We thus provide a platform for academic and industrial researchers to showcase their latest work, share research ideas, discuss various challenges, and identify areas where further research is needed in pre-training, fine-tuning, and prompt-learning methods for large-scale AI models. We foster the development of a strong research community focused on solving challenges related to large-scale AI models, providing superior and impactful strategies that can change people's lives in the future.

AI Applications uses various data science tools such as Jupyter notebook to prescribe a series of steps, commonly referred as workflow, for building AI Solutions. The steps in workflow can be as simple as loading the data from remote storage, visualize the data for better understanding or conducting data quality study, or it can be as complex as generating features for modeling, best model discovery processes, etc. Clearly, different steps of the data science workflow has varying requirement of compute resources. Moreover, the execution of steps in workflow are Adhoc and Subjective. With wider availability of various Serverless technology, in this paper, we demonstrate a generalized framework that can be used to provide on demand scale out capability for the Data Science Workflow. In particular, we selected the most common AI operation, namely Automatic Model Selection, as an example to demonstrate benefits of serverless computing. We conducted a detailed experimental results using IBM Code Engine technology to validate the benefits of our proposed approach.

This tutorial presents a design and implementation of a scikit-compatible system for detecting anomalies from time series data for the purpose of offering a broad range of algorithms to the end user, with special focus on unsupervised/semi-supervised learning. Given an input time series, we discuss how data scientist can construct four categories of anomaly pipelines followed by an enrichment module that helps to label anomaly. The tutorial provides an hand-on-experience using a deployed system on IBM API Hub for developer communities that aim to support a wide range of execution engines to meet the diverse need of anomaly workloads such as Serveless for CPU intensive work, GPU for deep-learning model training, etc.

Time series anomaly detection is an interesting practical problem that mostly falls into unsupervised learning segment. There has been continuous stream of work being published in top-tier data mining and machine learning conferences. We invented many anomaly algorithms, procedures, and applications while working on real industrial application settings. This tutorial presents a design and implementation of a scikit-compatible system for detecting anomalies from time series data for the purpose of offering a broad range of algorithms to the end user, with special focus on unsupervised/semi-supervised learning.

This poster paper presents an efficient design of deploying anomaly detection service using serverless technology. Our design is motivated by the fact that the workload originating from the service calls are adhoc and reserving the infrastructure upfront is not advisable. To address this, we utilized the emerging serverless platform for executing the incoming training request. Our extensive experimental analysis demonstrate the usefulness of the proposed idea.

Assets in the domain of Internet of Things (IoT) generate time-series data such as sensor readings and alerts. In addition, the assets have associated static data such as the make, model and other manufacturing information. The sensors in the asset components may have implicit relationships with each other, which are not interpretable without domain knowledge. Many problems exist which involve computation of relationships between sensors or subsystems in the asset components. Typically, the number of sensors in a real world asset may range anywhere from tens to thousands of sensors - and in this case, finding relationships between them becomes a highly computationally intensive task. In this paper, we study one such problem of anomaly detection in industrial data based on the functioning of the sensors and their interrelationships in both normal and abnormal conditions. We further demonstrate the issue of run-time and performance complexity in this problem, and present a speed-up strategy using Serverless Computing for parallelization, and demonstrate the usefulness of this method by comparing the speed-up achieved.

We present a novel framework for multivariate time series representation learning based on the transformer encoder architecture. The framework includes an unsupervised pre-training scheme, which can offer substantial performance benefits over fully supervised learning on downstream tasks, both with but even without leveraging additional unlabeled data, i.e., by reusing the existing data samples. Evaluating our framework on several public multivariate time series datasets from various domains and with diverse characteristics, we demonstrate that it performs significantly better than the best currently available methods for regression and classification, even for datasets which consist of only a few hundred training samples. Given the pronounced interest in unsupervised learning for nearly all domains in the sciences and in industry, these findings represent an important landmark, presenting the first unsupervised method shown to push the limits of state-of-the-art performance for multivariate time series regression and classification.

A large number of time series forecasting models including traditional statistical models, machine learning models and more recently deep learning have been proposed in the literature. However, choosing the right model along with good parameter values that performs well on a given data is still challenging. Automatically providing a good set of models to users for a given dataset saves both time and effort from using trial-and-error approaches with a wide variety of available models along with parameter optimization. We present AutoAI for Time Series Forecasting (AutoAI-TS) that provides users with a zero configuration (zero-conf) system to efficiently train, optimize and choose best forecasting model among various classes of models for the given dataset. With its flexible zero-conf design, AutoAI-TS automatically performs all the data preparation, model creation, parameter optimization, training and model selection for users and provides a trained model that is ready to use. For given data, AutoAI-TS utilizes a wide variety of models including classical statistical models, Machine Learning (ML) models, statistical-ML hybrid models and deep learning models along with various transformations to create forecasting pipelines. It then evaluates and ranks pipelines using the proposed T-Daub mechanism to choose the best pipeline. The paper describe in detail all the technical aspects of AutoAI-TS along with extensive benchmarking on a variety of real world data sets for various use-cases. Benchmark results show that AutoAI-TS, with no manual configuration from the user, automatically trains and selects pipelines that on average outperform existing state-of-the-art time series forecasting toolkits.

Data quality assessment is an essential process of any data analysis process including machine learning. The process is time-consuming as it involves multiple independent data quality checks that are performed iteratively at scale on evolving data resulting from exploratory data analysis (EDA). Existing solutions that provide computational optimizations for data quality assessment often separate the data structure from its data quality which then requires efforts from users to explicitly maintain state-like information. They demand a certain level of distributed system knowledge to ensure high-level pipeline optimizations from data analysts who should instead be focusing on analyzing the data. We, therefore, propose data-quality-aware dataframes, a data quality management system embedded as part of a data analyst's familiar data structure, such as a Python dataframe. The framework automatically detects changes in datasets' metadata and exploits the context of each of the quality checks to provide efficient data quality assessment on ever-changing data. We demonstrate in our experiment that our approach can reduce the overall data quality evaluation runtime by 40-80% in both local and distributed setups with less than 10% increase in memory usage.

In this paper, we describe an overarching ML system with a simple programming interface that leverages existing AI and ML frameworks to make the task of model exploration easier. The proposed system introduces a new programming construct namely pipeline graph (a directed acyclic graph) consisting of multiple machine learning operations provided by different ML repositories. End user uses the pipeline graph as a common interface for modeling different ML tasks such as classification, regression, and timeseries prediction, while enabling efficient execution on different environments (Spark, Celery and Cloud). We further annotated the pipeline graph with a hyper-parameter grid and an option to try-out a wide range of optimization strategies (i.e., Random, Bayesian, Bandit, AutoLearn, etc). Given a large pre-defined pipeline graph along with its hyper-parameters, we provided a general-purpose, scalable and efficient pipeline-graph exploration technique to provide the automated solutions to a variety of ML tasks. We compare our automated approach to several state-of-the-art automated AI systems and find that we achieve performance comparable to the best results, while often producing simpler pipelines using off the shelf components. Our evaluation suite consists of experiments on 60+ classifications and regressions datasets.

Time series value forecasting using machine learning models utilizing time series features has recently got good attention of Time series analytics community. This paper proposes an automated feature learning mechanisms to filter out most useful features from hundreds of available features for time series prediction problems. The paper further proposes a novel mechanism to dynamically filter features that are most suitable for the given input time series data. With such mechanisms we create pipeline consisting of most useful features for given input data and increases the performance of the prediction model. Our proposed mechanism first, groups well known features for time series analysis, generates and assigns the features importance score using multiple scoring configurations. Once scores are assigned, features are filtered using a threshold that is derived using reference feature score and Critical Difference diagram. The filtered features are subsequently analyzed based on the characteristics of the input dataset. We show using experimental results that our approach of input data based dynamic feature selection improves the overall performance of machine learning models compared to the case where dynamic feature extraction is not applied prior to modeling.

The success of IoT depends on our ability to solve challenging problems which were previously infeasible. One of the most critical challenges in IoT space is the preventive maintenance in industrial manufacturing processes to maximize equipment availability and durability. Traditionally, preventive management only follows less cost-effective strategies, say time or usage based management. With large amount sensor data harvested from IoT, we can develop much more intelligent predictive maintenance based on accurate machinery failure prediction. In this paper, we develop a framework named DoM (Doctor for Machines) to produce the best predictive model for several oil and gas industry engagements. Our framework is built in the form of pipeline that allows us to generate multiple models simultaneously with parallel computing. We configure the modeling process by assigned different machine learning tasks as such sampling, feature extraction, modeling, and post-processing into the pipeline. The pipeline forms a machine learning graph workflow. With the automation of execution all the tasks in the workflow, the client can easily choose a best predictive model fitting their failure tolerance. We have successfully applied DoM to six data sets, and identified valuables insights on the best practices of creating predictive model. Our clients have successfully achieved financial benefits by applying DoM to develop predictive maintenance schemes to their expensive equipment.

Data Quality (DQ) has been one of the key focuses as Data Analytics and Artificial Intelligence (AI) fields continue to grow. Yet, data quality analysis has mostly been a disjointed, ad-hoc, and cumbersome process in the overall data analysis workflow. There have been ongoing attempts to formalize this process, but the solutions that have come out are not universally applicable. Most of the proposed solutions try to address the problem of data quality from a limited perspective and suc-cessfully address only a subset of all challenges. These solutions fail to translate to other domains due to a lack of structure. In this paper, we present DQLearn, a toolkit for structured data quality learning. We start by presenting the core principle on which we build our library and introduce the four components that provide a solid base to address the needs of the data quality problem. Then, we showcase our automation structure - "Workflows", and the two optimization techniques equipped with it, that help the users to structure their learning problem very easily. Next, we discuss four important scenarios of the DQ Workflows in the overall life-cycle. Finally, we demonstrate the utility of the proposed toolkit with public datasets and show benchmark results from optimization experiments.

This paper proposes a verifiable imputation process and an enabling tool for univariate time series. Common ad-hoc and case-specific imputation are not enough to ensure high quality and effective imputation. We adopt the similar verification logic of supervised learning. We use artificial missing sampling as the test set to estimate a set of imputers' performances and use the estimated performances to select the best imputer. To ensure the correctness of selection, we analyze the impact of various factors on estimation accuracy. Those factors are missing rate, size of artificial missing data and patterns, selected imputers, and noise level. We propose a two-step verifiable imputation process to integrate all of the steps. With this process, we can always leverage the most suitable imputer to achieve a high quality of imputation without tedious and error-prone data cleaning efforts. We implement the tool as a Python package, with many imputers with their unique capabilities and a API. We automate the imputation through a standard process, which returns imputed results and detailed rationales of selection along with quality metrics.

Fueled with growth in the fields of Internet of Things (IoT) and Big Data, data has become one of the most valuable assets in today's world. While we are leveraging this data for analyzing complex systems using machine learning and deep learning, a considerable amount of time and effort is spent on addressing data quality issues. If undetected, data quality issues can cause large deviations in the analysis, misleading data scientists. To ease the effort of identifying and addressing data quality challenges, we introduce DQA, a scalable, automated and interactive data quality advisor. In this paper, we describe the DQA framework, provide detailed description of its components and the benefits of integrating it in a data science process. We propose a programmatic approach for implementing the data quality framework which automatically generates dynamic executable graphs for performing data validations fine-tuned for a given dataset. We discuss the use of DQA to build a library of validation checks common to many applications. We provide insight into how DQA addresses many persistence and usability issues which currently make data cleaning a laborious task for data scientists. Finally, we provide a case study of how DQA is implemented in a realworld system and describe the benefits realized.

Word, sentence and document embeddings have become the cornerstone of most natural language processing-based solutions. The training of an effective embedding depends on a large corpus of relevant documents. However, such corpus is not always available, especially for specialized heavy industries such as oil, mining, or steel. To address the problem, this paper proposes a semi-supervised learning framework to create document corpus and embedding starting from an industry taxonomy, along with a very limited set of relevant positive and negative documents. Our solution organizes candidate documents into a graph and adopts different explore and exploit strategies to iteratively create the corpus and its embedding. At each iteration, two metrics, called Coverage and Context Similarity, are used as proxy to measure the quality of the results. Our experiments demonstrate how an embedding created by our solution is more effective than the one created by processing thousands of industry-specific document pages. We also explore using our embedding in downstream tasks, such as building an industry specific classification model given labeled training data, as well as classifying unlabeled documents according to industry taxonomy terms.

Discovering the underlying dynamics leading up to an industrial asset failure is an important problem to be solved for successful development of Predictive Maintenance techniques. Existing work has largely focused on building complex ML/AI models for developing Predictive Maintenance solution patterns, but has largely avoided developing methods to explain the underlying failure dynamics. In this paper, we use an old but significantly improved change-pattern based technique to analyze IoT sensor data and failure information to generate useful and interpretable failure-centric insight. We discuss a solution pattern that we call ChieF, which when applied on multi-variate time series datasets, discover the leading failure indicators, generate associative patterns among multiple features, and output temporal dynamics of changes. Experimental analysis of ChieF on four datasets uncovers insights that may be valuable for predictive maintenance.

Increasing popularity of Cyber Physical System in Industry and automation applications generate a large amount of sensor data using IoT Devices. Majority of these sensed data are materialized in the form of interval events, i.e., event with duration. The temporal relationship between interval events, known as Interval Pattern, has many useful applications like, in human activity detection, patient monitoring and anomaly detection, etc. Existing work on Cyber Physical System have not incorporated the interval event analysis. In this paper, we examine the need of interval pattern discovery in CPS and propose a novel efficient algorithm called STIPA (Shrinkable Temporal Index based Pattern-growth Algorithm) for discovering the frequent interval patterns. Existing pattern-growth based interval pattern mining solutions keep index information in memory whereas index size increases monotonically as the length of pattern increases. As a result, existing solutions are not suitable to run pattern mining algorithm on devices which have limited memory. However, STIPA is equipped with a memory efficient indexing technique whose index size shrinks as the length of prefix increases in interval patterns. Moreover, a compressed interval pattern representation is also introduced which further reduces the memory requirement. Our performance study on synthetic and real-world dataset shows that STIPA demands less memory in comparison to existing techniques and it also outperforms the existing methods in execution time.

Named Entity Identification (NEI) is the task of identifying named entities from textual data. While NEI for English language can be done with considerable accuracy owing to tools like Stanford NER tagger, the accuracy in case of Indian languages like Hindi is comparatively poor. One of the reasons for this is the lack of sufficiently large annotated corpora in Indian languages on which NE-taggers can be trained. In this paper, we describe a lightweight, automated process of tagging named entities in Hindi news headlines to create a huge silver standard corpus of NE-tagged news headlines. We show, via experiments, that the use of our corpus to train NE-taggers produces comparable results to the use of gold standard training corpus. Although we have applied the process majorly to Hindi language only, our method can also be applied to other languages provided they fulfill certain requirements which are necessitated by our process.

News-casters are Twitter users who periodically pick up interesting news from online news media and spread it to their followers' network. Existing works on Twitter user analysis have only analysed a pre-defined set of users for user modeling, influence analysis and news recommendation. The problem of identifying prominent, trustworthy and consistent news-casters is unaddressed so far. In this paper, we present a framework, NCFinder, to discover top-k consistent news-casters directly from Twitter. NCFinder uses news headlines published in online news sources to periodically collect authentic news-tweets and processes them to discover news-casters, news sources and news concepts. Next, NCFinder builds a tripartite graph among news-casters, news source and news concepts and employs HITS algorithm on it to score the news-casters on daily basis. The daily score profiles of the news-casters collected over a time-period are then used to infer top-$k$ consistent news-casters. We run NCFinder from 11th Nov. to 24th Nov., 2014 and discover top-100 consistent news-casters and their profile information.

A moving object cluster is a set of objects that move close to each other for a long time interval. Existing works have utilized object trajectories to discover moving object clusters efficiently. In this article, we define a spatiotemporal influence-based moving cluster that captures spatiotemporal influence spread over a set of spatial objects. A spatiotemporal influence-based moving cluster is a sequence of spatial clusters, where each cluster is a set of nearby objects, such that each object in a cluster influences at least one object in the next immediate cluster and is also influenced by an object from the immediate preceding cluster. Real-life examples of spatiotemporal influence-based moving clusters include diffusion of infectious diseases and spread of innovative ideas. We study the discovery of spatiotemporal influence-based moving clusters in a database of spatiotemporal events. While the search space for discovering all spatiotemporal influence-based moving clusters is prohibitively huge, we design a method, STIMer, to efficiently retrieve the maximal answer. The algorithm STIMer adopts a top-down recursive refinement method to generate the maximal spatiotemporal influence-based moving clusters directly. Empirical studies on the real data as well as large synthetic data demonstrate the effectiveness and efficiency of our method.

Many frequent pattern mining algorithms have been developed for categorical, numerical, time series, or interval data. However, little attention has been given to integrate these algorithms so as to mine frequent patterns from multiple domain datasets for classification. In this paper, we introduce the notion of a heterogenous pattern to capture the associations among different kinds of data. We propose a unified framework for mining multiple domain datasets and design an iterative algorithm called HTMiner. HTMiner discovers essential heterogenous patterns for classification and performs instance elimination. This instance elimination step reduces the problem size progressively by removing training instances which are correctly covered by the discovered essential heterogenous pattern. Experiments on two real world datasets show that the HTMiner is efficient and can significantly improve the classification accuracy.

Trajectory classification has many useful applications. Existing works on trajectory classification do not consider the duration information of trajectory. In this paper, we extract duration-aware features from trajectories to build a classifier. Our method utilizes information theory to obtain regions where the trajectories have similar speeds and directions. Further, trajectories are summarized into a network based on the MDL principle that takes into account the duration difference among trajectories of different classes. A graph traversal is performed on this trajectory network to obtain the top-k covering path rules for each trajectory. Based on the discovered regions and top-k path rules, we build a classifier to predict the class labels of new trajectories. Experiment results on real-world datasets show that the proposed duration-aware classifier can obtain higher classification accuracy than the state-of-the-art trajectory classifier.

Existing temporal pattern mining assumes that events do not have any duration. However, events in many real world applications have durations, and the relationships among these events are often complex. These relationships are modeled using a hierarchical representation that extends Allen's interval algebra. However, this representation is lossy as the exact relationships among the events cannot be fully recovered. In this paper, we augment the hierarchical representation with additional information to achieve a lossless representation. An efficient algorithm called IEMiner is designed to discover frequent temporal patterns from interval-based events. The algorithm employs two optimization techniques to reduce the search space and remove non-promising candidates. From the discovered temporal patterns, we build an interval-based classifier called IEClassifier to differentiate closely related classes. Experiments on both synthetic and real world datasets indicate the efficiency and scalability of the proposed approach, as well as the improved accuracy of IEClassifier.