Mossad Helali, Yutai Luo, Tae Jun Ham, Jim Plotts, Ashwin Chaugule, Jichuan Chang, Parthasarathy Ranganathan, Essam Mansour. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

In recent years, we have witnessed the growing interest from academia and industry in applying data science technologies to analyze large amounts of data. In this process, a myriad of artifacts (datasets, pipeline scripts, etc.) are created. However, there has been no systematic attempt to holistically collect and exploit all the knowledge and experiences that are implicitly contained in those artifacts. Instead, data scientists recover information and expertise from colleagues or learn via trial and error. Hence, this paper presents a scalable platform, KGLiDS, that employs machine learning and knowledge graph technologies to abstract and capture the semantics of data science artifacts and their connections. Based on this information, KGLiDS enables various downstream applications, such as data discovery and pipeline automation. Our comprehensive evaluation covers use cases in data discovery, data cleaning, transformation, and AutoML. It shows that KGLiDS is significantly faster with a lower memory footprint than the state-of-the-art systems while achieving comparable or better accuracy.

AutoML systems build machine learning models automatically by performing a search over valid data transformations and learners, along with hyper-parameter optimization for each learner. Many AutoML systems use meta-learning to guide search for optimal pipelines. In this work, we present a novel meta-learning system called KGpip which (1) builds a database of datasets and corresponding pipelines by mining thousands of scripts with program analysis, (2) uses dataset embeddings to find similar datasets in the database based on its content instead of metadata-based features, (3) models AutoML pipeline creation as a graph generation problem, to succinctly characterize the diverse pipelines seen for a single dataset. KGpip's meta-learning is a sub-component for AutoML systems. We demonstrate this by integrating KGpip with two AutoML systems. Our comprehensive evaluation using 121 datasets, including those used by the state-of-the-art systems, shows that KGpip significantly outperforms these systems.

Data science growing success relies on knowing where a relevant dataset exists, understanding its impact on a specific task, finding ways to enrich a dataset, and leveraging insights derived from it. With the growth of open data initiatives, data scientists need an extensible set of effective discovery operations to find relevant data from their enterprise datasets accessible via data discovery systems or open datasets accessible via data portals. Existing portals and systems suffer from limited discovery support and do not track the use of a dataset and insights derived from it. We will demonstrate KGLac, a system that captures metadata and semantics of datasets to construct a knowledge graph (GLac) interconnecting data items, e.g., tables and columns. KGLac supports various data discovery operations via SPARQL queries for table discovery, unionable and joinable tables, plus annotation with related derived insights. We harness a broad range of Machine Learning (ML) approaches with GLac to enable automatic graph learning for advanced and semantic data discovery. The demo will showcase how KGLac facilitates data discovery and enrichment while developing an ML pipeline to evaluate potential gender salary bias in IT jobs.

In this paper, we analyze a wide range of physiological, behavioral, performance, and subjective measures to estimate cognitive load (CL) during e-learning. To the best of our knowledge, the analyzed sensor measures comprise the most diverse set of features from a variety of modalities that have to date been investigated in the e-learning domain. Our focus lies on predicting the subjectively reported CL and difficulty as well as intrinsic content difficulty based on the explored features. A study with 21 participants, who learned through videos and quizzes in a Moodle environment, shows that classifying intrinsic content difficulty works better for quizzes than for videos, where participants actively solve problems instead of passively consuming videos. Regression analysis for predicting the subjectively reported level of CL and difficulty also works with very low error within content topics. Among the explored feature modalities, eye-based features yield the best results, followed by heart-based and then skin-based measures. Furthermore, combining multiple modalities results in better performance compared to using a single modality. The presented results can guide researchers and developers of cognition-aware e-learning environments by suggesting modalities and features that work particularly well for estimating difficulty and CL.