Unionable table search techniques input a query table from a user and search for data lake tables that can contribute additional rows to the query table. The definition of unionability is generally based on similarity measures which may include similarity between columns (e.g., value overlap or semantic similarity of the values in the columns) or tables (e.g., similarity of table embeddings). Due to this and the large redundancy in many data lakes (which can contain many copies and versions of the same table), the most unionable tables may be identical or nearly identical to the query table and may contain little new information. Hence, we introduce the problem of identifying unionable tuples from a data lake that are diverse with respect to the tuples already present in a query table. We perform an extensive experimental analysis of well-known diversity algorithms applied to this novel problem and identify a gap that we address with a novel, clustering-based tuple diversity algorithm called DUST. DUST uses a novel embedding model to represent unionable tuples that outperforms other tuple representation models by at least 15 % when representing unionable tuples. Using real data lake benchmarks, we show that our diversification algorithm is more than six times faster than the most efficient diversification baseline. We also show that it is more effective in diversifying unionable tuples than existing diversification algorithms.

Urban environments are continuously mapped and modeled by various data collection platforms, including satellites, unmanned aerial vehicles and street cameras. The growing availability of 3D geospatial data from multiple modalities has introduced new opportunities and challenges for integrating spatial knowledge at scale, particularly in high-impact domains such as urban planning and rapid disaster management. Geospatial entity resolution is the task of identifying matching spatial objects across different datasets, often collected independently under varying conditions. Existing approaches typically rely on spatial proximity, textual metadata, or external identifiers to determine correspondence. While useful, these signals are often unavailable, unreliable, or misaligned, especially in cross-source scenarios. To address these limitations, we shift the focus to the intrinsic geometry of 3D spatial objects and present 3dSAGER (3D Spatial-Aware Geospatial Entity Resolution), an end-to-end pipeline for geospatial entity resolution over 3D objects. 3dSAGER introduces a novel, spatial-reference-independent featurization mechanism that captures intricate geometric characteristics of matching pairs, enabling robust comparison even across datasets with incompatible coordinate systems where traditional spatial methods fail. As a key component of 3dSAGER, we also propose a new lightweight and interpretable blocking method, BKAFI, that leverages a trained model to efficiently generate high-recall candidate sets. We validate 3dSAGER through extensive experiments on real-world urban datasets, demonstrating significant gains in both accuracy and efficiency over strong baselines. Our empirical study further dissects the contributions of each component, providing insights into their impact and the overall design choices.

Multiple versions of the same dataset can exist in a data repository (e.g., data warehouses, data lakes, etc.), mainly because of the interactive and collaborative nature of data science. Data creators generally update existing datasets and upload them as new datasets to data repositories without proper documentation. Identifying such versions helps in data management, data governance, and making better decisions using data. However, there is a dearth of benchmarks to develop and evaluate data versioning techniques, which requires a lot of human effort. Thus, this work introduces a novel framework to generate benchmarks for data versioning using Generative AI (specifically Large Language Models). The proposed framework offers properties that existing benchmarks do not have, including proper documentation, version lineage, and complex transformations generated by an LLM. We also share VerLLM-v1, the first version of the benchmark that features these properties, and compare it to existing benchmarks.

We introduce the problem of Table Reclamation. Given a Source Table and a large table repository, reclamation finds a set of tables that, when integrated, reproduce the source table as closely as possible. Unlike query discovery problems like Query-by-Example or by-Target, Table Reclamation focuses on reclaiming the data in the Source Table as fully as possible using real tables that may be incomplete or inconsistent. To do this, we define a new measure of table similarity, called error-aware instance similarity, to measure how close a reclaimed table is to a Source Table, a measure grounded in instance similarity used in data exchange. Our search covers not only Select-project-join queries, but integration queries with unions, outerjoins, and the unary operators subsumption and complementation that have been shown to be important in data integration and fusion. Using reclamation, a data scientist can understand if any tables in a repository can be used to exactly reclaim a tuple in the Source. If not, one can understand if this is due to differences in values or to incompleteness in the data. Our solution, Gen-T, performs table discovery to retrieve a set of candidate tables from the table repository, filters these down to a set of originating tables, then integrates these tables to reclaim the Source as closely as possible. We show that our solution, while approximate, is accurate, efficient and scalable in the size of the table repository with experiments on real data lakes containing up to 15K tables, where the average number of tuples varies from small (web tables) to extremely large (open data tables) up to 1M tuples.

Virtual Knowledge Graphs (VKGs) constitute one of the most promising paradigms for integrating and accessing legacy data sources. A critical bottleneck in the integration process involves the definition, validation, and maintenance of mapping assertions that link data sources to a domain ontology. To support the management of mappings throughout their entire lifecycle, we identify a comprehensive catalog of sophisticated mapping patterns that emerge when linking databases to ontologies. To do so, we build on well-established methodologies and patterns studied in data management, data analysis, and conceptual modeling. These are extended and refined through the analysis of concrete VKG benchmarks and real-world use cases, and considering the inherent impedance mismatch between data sources and ontologies. We validate our catalog on the considered VKG scenarios, showing that it covers the vast majority of mappings present therein.

Entity matching, a core data integration problem, is the task of deciding whether two data tuples refer to the same real-world entity. Recent advances in deep learning methods, using pre-trained language models, were proposed for resolving entity matching. Although demonstrating unprecedented results, these solutions suffer from a major drawback as they require large amounts of labeled data for training, and, as such, are inadequate to be applied to low resource entity matching problems. To overcome the challenge of obtaining sufficient labeled data we offer a new active learning approach, focusing on a selection mechanism that exploits unique properties of entity matching. We argue that a distributed representation of a tuple pair indicates its informativeness when considered among other pairs. This is used consequently in our approach that iteratively utilizes space-aware considerations. Bringing it all together, we treat the low resource entity matching problem as a Battleship game, hunting indicative samples, focusing on positive ones, through awareness of the latent space along with careful planning of next sampling iterations. An extensive experimental analysis shows that the proposed algorithm outperforms state-of-the-art active learning solutions to low resource entity matching, and although using less samples, can be as successful as state-of-the-art fully trained known algorithms.

Entity resolution, a longstanding problem of data cleaning and integration, aims at identifying data records that represent the same real-world entity. Existing approaches treat entity resolution as a universal task, assuming the existence of a single interpretation of a real-world entity and focusing only on finding matched records, separating corresponding from non-corresponding ones, with respect to this single interpretation. However, in real-world scenarios, where entity resolution is part of a more general data project, downstream applications may have varying interpretations of real-world entities relating, for example, to various user needs. In what follows, we introduce the problem of multiple intents entity resolution (MIER), an extension to the universal (single intent) entity resolution task. As a solution, we propose FlexER, utilizing contemporary solutions to universal entity resolution tasks to solve MIER. FlexER addresses the problem as a multi-label classification problem. It combines intent-based representations of tuple pairs using a multiplex graph representation that serves as an input to a graph neural network (GNN). FlexER learns intent representations and improves the outcome to multiple resolution problems. A large-scale empirical evaluation introduces a new benchmark and, using also two well-known benchmarks, shows that FlexER effectively solves the MIER problem and outperforms the state-of-the-art for a universal entity resolution.

Existing techniques for unionable table search define unionability using metadata (tables must have the same or similar schemas) or column-based metrics (for example, the values in a table should be drawn from the same domain). In this work, we introduce the use of semantic relationships between pairs of columns in a table to improve the accuracy of the union search. Consequently, we introduce a new notion of unionability that considers relationships between columns, together with the semantics of columns, in a principled way. To do so, we present two new methods to discover the semantic relationships between pairs of columns. The first uses an existing knowledge base (KB), and the second (which we call a "synthesized KB") uses knowledge from the data lake itself. We adopt an existing Table Union Search benchmark and present new (open) benchmarks that represent small and large real data lakes. We show that our new unionability search algorithm, called SANTOS, outperforms a state-of-the-art union search that uses a wide variety of column-based semantics, including word embeddings and regular expressions. We show empirically that our synthesized KB improves the accuracy of union search by representing relationship semantics that may not be contained in an available KB. This result hints at a promising future of creating synthesized KBs from data lakes with limited KB coverage and using them for union search.

In multi-user environments in which data science and analysis is collaborative, multiple versions of the same datasets are generated. While managing and storing data versions has received some attention in the research literature, the semantic nature of such changes has remained under-explored. In this work, we introduce Explain-Da-V, a framework aiming to explain changes between two given dataset versions. Explain-Da-V generates explanations that use data transformations to explain changes. We further introduce a set of measures that evaluate the validity, generalizability, and explainability of these explanations. We empirically show, using an adapted existing benchmark and a newly created benchmark, that Explain-Da-V generates better explanations than existing data transformation synthesis methods.

We have made tremendous strides in providing tools for data scientists to discover new tables useful for their analyses. But despite these advances, the proper integration of discovered tables has been under-explored. An interesting semantics for integration, called Full Disjunction, was proposed in the 1980's, but there has been little progress in using it for data science to integrate tables culled from data lakes. We provide ALITE, the first proposal for scalable integration of tables that may have been discovered using join, union or related table search. We empirically show that ALITE can outperform previous algorithms for computing the Full Disjunction. ALITE relaxes previous assumptions that tables share common attribute names (which completely determine the join columns), are complete (without null values), and have acyclic join patterns. To evaluate ALITE, we develop and share three new benchmarks for integration that use real data lake tables.

Industry 4.0 offers opportunities to combine multiple sensor data sources using IoT technologies for better utilization of raw material in production lines. A common belief that data is readily available (the big data phenomenon), is oftentimes challenged by the need to effectively acquire quality data under severe constraints. In this paper we propose a design methodology, using active learning to enhance learning capabilities, for building a model of production outcome using a constrained amount of raw material training data. The proposed methodology extends existing active learning methods to effectively solve regression-based learning problems and may serve settings where data acquisition requires excessive resources in the physical world. We further suggest a set of qualitative measures to analyze learners performance. The proposed methodology is demonstrated using an actual application in the milk industry, where milk is gathered from multiple small milk farms and brought to a dairy production plant to be processed into cottage cheese.

Matching is a task at the heart of any data integration process, aimed at identifying correspondences among data elements. Matching problems were traditionally solved in a semi-automatic manner, with correspondences being generated by matching algorithms and outcomes subsequently validated by human experts. Human-in-the-loop data integration has been recently challenged by the introduction of big data and recent studies have analyzed obstacles to effective human matching and validation. In this work we characterize human matching experts, those humans whose proposed correspondences can mostly be trusted to be valid. We provide a novel framework for characterizing matching experts that, accompanied with a novel set of features, can be used to identify reliable and valuable human experts. We demonstrate the usefulness of our approach using an extensive empirical evaluation. In particular, we show that our approach can improve matching results by filtering out inexpert matchers.

Schema matching is at the heart of integrating structured and semi-structured data with applications in data warehousing, data analysis recommendations, Web table matching, etc. Schema matching is known as an uncertain process and a common method to overcome this uncertainty introduces a human expert with a ranked list of possible schema matches to choose from, known as top-Kmatching. In this work we propose a learning algorithm that utilizes an innovative set of features to rerank a list of schema matches and improves upon the ranking of the best match. We provide a bound on the size of an initial match list, tying the number of matches with a desired level of confidence in finding the best match. We also propose the use of matching predictors as features in a learning task, and tailored nine new matching predictors for this purpose. The proposed algorithm assists the matching process by introducing a quality set of alternative matches to a human expert. It also serves as a step towards eliminating the involvement of human experts as decision makers in a matching process altogether. A large scale empirical evaluation with real-world benchmark shows the effectiveness of the proposed algorithmic solution.

Measuring key performance indicators, such as queue lengths and waiting times, using event logs serve for improvement of resource-driven business processes. However, existing techniques assume the availability of complete life cycle information, including the time a case was scheduled for execution (aka arrival times). Yet, in practice, such information may be missing for a large portion of the recorded cases. In this paper, we propose a methodology to address missing life-cycle data by incorporating predicted information in business processes performance analysis. Our approach builds upon techniques from queueing theory and leverages supervised learning to accurately predict performance indicators based on an event log with missing data. Our experimental results using both synthetic and real-world data demonstrate the effectiveness of our approach.

We address the web table retrieval task, aiming to retrieve and rank web tables as whole answers to a given information need. To this end, we formally define web tables as multimodal objects. We then suggest a neural ranking model, termed MTR, which makes a novel use of Gated Multimodal Units (GMUs) to learn a joint-representation of the query and the different table modalities. We further enhance this model with a co-learning approach which utilizes automatically learned query-independent and query-dependent "helper'' labels. We evaluate the proposed solution using both ad hoc queries (WikiTables) and natural language questions (GNQtables). Overall, we demonstrate that our approach surpasses the performance of previously studied state-of-the-art baselines.

We present InCognitoMatch, the first cognitive-aware crowdsourcing application for matching tasks. InCognitoMatch provides a handy tool to validate, annotate, and correct correspondences using the crowd whilst accounting for human matching biases. In addition, InCognitoMatch enables system administrators to control context information visible for workers and analyze their performance accordingly. For crowd workers, InCognitoMatch is an easy-to-use application that may be accessed from multiple crowdsourcing platforms. In addition, workers completing a task are offered suggestions for followup sessions according to their performance in the current session. For this demo, the audience will be able to experience InCognitoMatch thorough three use-cases, interacting with system as workers and as administrators.

Given a keyword query, the ad hoc table retrieval task aims at retrieving a ranked list of the top-k most relevant tables in a given table corpus. Previous works have primarily focused on designing table-centric lexical and semantic features, which could be utilized for learning-to-rank (LTR) tables. In this work, we make a novel use of intrinsic (passage-based) and extrinsic (manifold-based) table similarities for enhanced retrieval. Using the WikiTables benchmark, we study the merits of utilizing such similarities for this task. To this end, we combine both similarity types via a simple, yet an effective, cascade re-ranking approach. Overall, our proposed approach results in a significantly better table retrieval quality, which even transcends that of strong semantically-rich baselines.

Schema matching is a process that serves in integrating structured and semi-structured data. Being a handy tool in multiple contemporary business and commerce applications, it has been investigated in the fields of databases, AI, Semantic Web, and data mining for many years. The core challenge still remains the ability to create quality algorithmic matchers, automatic tools for identifying correspondences among data concepts ( e.g. , database attributes). In this work, we offer a novel post processing step to schema matching that improves the final matching outcome without human intervention. We present a new mechanism, similarity matrix adjustment , to calibrate a matching result and propose an algorithm (dubbed ADnEV) that manipulates, using deep neural networks, similarity matrices, created by state-of-the-art algorithmic matchers. ADnEV learns two models that iteratively adjust and evaluate the original similarity matrix. We empirically demonstrate the effectiveness of the proposed algorithmic solution for improving matching results, using real-world benchmark ontology and schema sets. We show that ADnEV can generalize into new domains without the need to learn the domain terminology, thus allowing cross-domain learning. We also show ADnEV to be a powerful tool in handling schemata which matching is particularly challenging. Finally, we show the benefit of using ADnEV in a related integration task of ontology alignment.

Discovery plays a key role in data-driven analysis of business processes. The vast majority of contemporary discovery algorithms aims at the identification of control-flow constructs. The increase in data richness, however, enables discovery that incorporates the context of process execution beyond the control-flow perspective. A "control-flow first" approach, where context data serves for refinement and annotation, is limited and fails to detect fundamental changes in the control-flow that depend on context data. In this work, we thus propose a novel approach for combining the control-flow and data perspectives under a single roof by extending inductive process discovery. Our approach provides criteria under which context data, handled through unsupervised learning, take priority over control-flow in guiding process discovery. The resulting model is a process tree, in which some operators carry data semantics instead of control-flow semantics. We evaluate the approach using synthetic and real-world datasets and show that the resulting models are superior to state-of-the-art discovery methods in terms of measures that are based on multi perspective alignments.

Schema matching is a task at the heart of integrating heterogeneous structured and semi-structured data with applications in data warehousing, process matching, data analysis recommendations, Web table matching, etc. Schema matching is known to be an uncertain process and a common method of overcoming this uncertainty is by introducing a human expert with a ranked list of possible schema matches from which the expert may choose, known astop-Kmatching. In this work we propose a learning algorithm that utilizes an innovative set of features to rerank a list of schema matches and improves upon the ranking of the best match. The proposed algorithm assists the matching process by introducing a quality set of alternative matches to a human expert. It also serves as a step towards eliminating the involvement of human experts as decision makers in a matching process altogether. A large scale empirical evaluation with real-world benchmark shows the effectiveness of the proposed algorithmic solution.

Share on (Artificial) Mind over Matter: Integrating Humans and Algorithms in Solving Matching Problems Author: Roee Shraga Technion - Israel Institute of Technology, Haifa, Israel Technion - Israel Institute of Technology, Haifa, IsraelView Profile Authors Info & Claims SIGMOD '18: Proceedings of the 2018 International Conference on Management of DataMay 2018 Pages 1813–1815https://doi.org/10.1145/3183713.3183716Published:27 May 2018Publication History 1citation149DownloadsMetricsTotal Citations1Total Downloads149Last 12 Months13Last 6 weeks2 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access