Recent advances in language models (LMs) open new opportunities for schema matching (SM). Recent approaches have shown their potential and key limitations: while small LMs (SLMs) require costly, difficult-to-obtain training data, large LMs (LLMs) demand significant computational resources and face context window constraints. We present Magneto, a cost-effective and accurate solution for SM that combines the advantages of SLMs and LLMs to address their limitations. By structuring the SM pipeline in two phases, retrieval and reranking, Magneto can use computationally efficient SLM-based strategies to derive candidate matches which can then be reranked by LLMs, thus making it possible to reduce runtime while improving matching accuracy. We propose (1) a self-supervised approach to fine-tune SLMs which uses LLMs to generate syntactically diverse training data, and (2) prompting strategies that are effective for reranking. We also introduce a new benchmark, developed in collaboration with domain experts, which includes real biomedical datasets and presents new challenges for SM methods. Through a detailed experimental evaluation, using both our new and existing benchmarks, we show that Magneto is scalable and attains high accuracy for datasets from different domains.

Relational data augmentation is a powerful technique for enhancing data analytics and improving machine learning models by incorporating columns from external datasets. However, it is challenging to efficiently discover relevant external tables to join with a given input table. Existing approaches rely on data discovery systems to identify “joinable” tables from external sources, typically based on overlap or containment. However, the sheer number of tables obtained from these systems results in irrelevant joins that need to be performed; this can be computationally expensive or even infeasible in practice. We address this limitation by proposing the use of efficient mutual information (MI) estimation for finding relevant joinable tables. We introduce a new sketching method that enables efficient evaluation of relationship discovery queries by estimating MI without materializing the joins and returning a smaller set of tables that are more likely to be relevant. We also demonstrate the effectiveness of our approach at approximating MI in extensive experiments using synthetic and real-world datasets.

Recently, Bessa et al. (PODS 2023) showed that sketches based on coordinated weighted sampling theoretically and empirically outperform popular linear sketching methods like Johnson-Lindentrauss projection and CountSketch for the ubiquitous problem of inner product estimation. We further develop this finding by introducing and analyzing two alternative sampling-based methods. In contrast to the computationally expensive algorithm in Bessa et al., our methods run in linear time (to compute the sketch) and perform better in practice, significantly beating linear sketching on a variety of tasks. For example, they provide state-of-the-art results for estimating the correlation between columns in unjoined tables, a problem that we show how to reduce to inner product estimation in a black-box way. While based on known sampling techniques (threshold and priority sampling) we introduce significant new theoretical analysis to prove approximation guarantees for our methods.

We present a new approach for independently computing compact sketches that can be used to approximate the inner product between pairs of high-dimensional vectors. Based on the Weighted MinHash algorithm, our approach admits strong accuracy guarantees that improve on the guarantees of popular linear sketching approaches for inner product estimation, such as CountSketch and Johnson-Lindenstrauss projection. Specifically, while our method exactly matches linear sketching for dense vectors, it yields significantly lower error for sparse vectors with limited overlap between non-zero entries. Such vectors arise in many applications involving sparse data, as well as in increasingly popular dataset search applications, where inner products are used to estimate data covariance, conditional means, and other quantities involving columns in unjoined tables. We complement our theoretical results by showing that our approach empirically outperforms existing linear sketches and unweighted hashing-based sketches for sparse vectors.

Dataset search is emerging as a critical capability in both research and industry: it has spurred many novel applications, ranging from the enrichment of analyses of real-world phenomena to the improvement of machine learning models. Recent research in this field has explored a new class of data-driven queries: queries consist of datasets and retrieve, from a large collection, related datasets. In this paper, we study a specific type of data-driven query that supports relational data augmentation through numerical data relationships: given an input query table, find the top-k tables that are both joinable with it and contain columns that are correlated with a column in the query. We propose a novel hashing scheme that allows the construction of a sketch-based index to support efficient correlated table search. We show that our proposed approach is effective and efficient, and achieves better trade-offs that significantly improve both the ranking accuracy and recall compared to the state-of-the-art solutions.

With the push for transparency and open data, many datasets and data repositories are becoming available on the Web. This opens new opportunities for data-driven exploration, from empowering analysts to answer new questions and obtain insights to improving predictive models through data augmentation. But as datasets are spread over a plethora of Web sites, finding data that are relevant for a given task is difficult. In this paper, we take a first step towards the construction of domain-specific data lakes. We propose an end-to-end dataset discovery system, targeted at domain experts, which given a small set of keywords, automatically finds potentially relevant datasets on the Web. The system makes use of search engines to hop across Web sites, uses online learning to incrementally build a model to recognize sites that contain datasets, utilizes a set of discovery actions to broaden the search, and applies a multi-armed bandit based algorithm to balance the trade-offs of different discovery actions. We report the results of an extensive experimental evaluation over multiple domains, and demonstrate that our strategy is effective and outperforms state-of-the-art content discovery methods.

Conflict researchers face many challenges, including (1) how to model conflicts, (2) how to measure them, (3) how to manage their spatio-temporal character, and (4) how to handle a potential abundance of information and explanation. In this paper, we describe an ecosystem of tools designed for use by subject matter experts that addresses these challenges. Three case studies show workflows that are facilitated by this ecosystem.

The increasing availability of structured datasets, from Web tables and open-data portals to enterprise data, opens up opportunities to enrich analytics and improve machine learning models through relational data augmentation. In this paper, we introduce a new class of data augmentation queries: join-correlation queries. Given a column Q and a join column KQ from a query table TQ, retrieve tables TX in a dataset collection such that TX is joinable with TQ on KQ and there is a column C ∈ TX such that Q is correlated with C. A naïve approach to evaluate these queries, which first finds joinable tables and then explicitly joins and computes correlations between Q and all columns of the discovered tables, is prohibitively expensive. To efficiently support correlated column discovery, we 1) propose a sketching method that enables the construction of an index for a large number of tables and that provides accurate estimates for join-correlation queries, and 2) explore different scoring strategies that effectively rank the query results based on how well the columns are correlated with the query. We carry out a detailed experimental evaluation, using both synthetic and real data, which shows that our sketches attain high accuracy and the scoring strategies lead to high-quality rankings.

The large volumes of structured data currently available, from Web tables to open-data portals and enterprise data, open up new opportunities for progress in answering many important scientific, societal, and business questions. However, finding relevant data is difficult. While search engines have addressed this problem for Web documents, there are many new challenges involved in supporting the discovery of structured data. We demonstrate how the Auctus dataset search engine addresses some of these challenges. We describe the system architecture and how users can explore datasets through a rich set of queries. We also present case studies which show how Auctus supports data augmentation to improve machine learning models as well as to enrich analytics.

The ability to continuously discover domain-specific content from the Web is critical for many applications. While focused crawling strategies have been shown to be effective for discovery, configuring a focused crawler is difficult and time-consuming. Given a domain of interest D, subject-matter experts (SMEs) must search for relevant websites and collect a set of representative Web pages to serve as training examples for creating a classifier that recognizes pages in D, as well as a set of pages to seed the crawl. In this paper, we propose DISCO, an approach designed to bootstrap domain-specific search. Given a small set of websites , DISCO aims to discover a large collection of relevant websites . DISCO uses a ranking-based framework that mimics the way users search for information on the Web: it iteratively discovers new pages, distills, and ranks them. It also applies multiple discovery strategies, including keyword-based and related queries issued to search engines, backward and forward crawling. By systematically combining these strategies, DISCO is able to attain high harvest rates and coverage for a variety of domains. We perform extensive experiments in four social-good domains, using data gathered by SMEs in the respective domains, and show that our approach is effective and outperforms state-of-the-art methods.

The ability to discover all content relevant to an information domain has many applications, from helping in the understanding of humanitarian crises to countering human and arms trafficking. In such applications, time is of essence: it is crucial to both maximize coverage and identify new content as soon as it becomes available, so that appropriate actions can be taken. In this paper, we propose new methods for efficient domain-specific re-crawling that maximize the yield for new content. By learning patterns of pages that have a high yield, our methods select a small set of pages that can be re-crawled frequently, increasing the coverage and freshness while conserving resources. Unlike previous approaches to this problem, our methods combine different factors to optimize the re-crawling strategy, do not require full snapshots for the learning step, and dynamically adapt the strategy as the crawl progresses. In an empirical evaluation, we have simulated the framework over 600 partial crawl snapshots in three different domains. The results show that our approach can achieve 150% higher coverage compared to existing, state-of-the-art techniques. In addition, it is also able to capture 80% of new relevant content within less than 4 hours of publication.

Web sites have adopted a variety of adversarial techniques to prevent web crawlers from retrieving their content. While it is possible to simulate users behavior using a browser to crawl such sites, this approach is not scalable. Therefore, understanding existing adversarial techniques is important to design crawling strategies that can adapt to retrieve the content as efficiently as possible. Ideally, a web crawler should detect the nature of the adversarial policies and select the most cost-effective means to defeat them.