Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks

Cappuzzo, Riccardo; Papotti, Paolo; Thirumuruganathan, Saravanan

doi:10.1145/3318464.3389742

Cited by 126 publications

(108 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our methodology shares the same spirit by requiring the definition of a data mapping (recall the paragraph with the same name in Section 2.2 ) and then providing a high degree of automation for the remaining phases. An interesting and recent approach to partially automate the definition of schema mappings uses Machine Learning algorithms (see, e.g., Cappuzzo et al (2020) ); it seems a promising line of future work also in our context.…”

Section: Discussionmentioning

confidence: 99%

Merging Datasets of CyberSecurity Incidents for Fun and Insight

et al. 2021

View full text Add to dashboard Cite

Providing an adequate assessment of their cyber-security posture requires companies and organisations to collect information about threats from a wide range of sources. One of such sources is history, intended as the knowledge about past cyber-security incidents, their size, type of attacks, industry sector and so on. Ideally, having a large enough dataset of past security incidents, it would be possible to analyze it with automated tools and draw conclusions that may help in preventing future incidents. Unfortunately, it seems that there are only a few publicly available datasets of this kind that are of good quality. The paper reports our initial efforts in collecting all publicly available security incidents datasets, and building a single, large dataset that can be used to draw statistically significant observations. In order to argue about its statistical quality, we analyze the resulting combined dataset against the original ones. Additionally, we perform an analysis of the combined dataset and compare our results with the existing literature. Finally, we present our findings, discuss the limitations of the proposed approach, and point out interesting research directions.

show abstract

Section: Discussionmentioning

confidence: 99%

Merging Datasets of CyberSecurity Incidents for Fun and Insight

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Recently, there has been effort to build a learned database systems [26] and an end-to-end learned optimizers [35,48]. DL has also been applied to the problem of entity resolution in [10] and data integration [4,51].…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Models for Selectivity Estimation of Multi-Attribute Queries

Hasan

Thirumuruganathan

Augustine

et al. 2020

Proceedings of the 2020 ACM SIGMOD International Conference on Management of Data

Self Cite

View full text Add to dashboard Cite

Selectivity estimation -the problem of estimating the result size of queries -is a fundamental problem in databases. Accurate estimation of query selectivity involving multiple correlated attributes is especially challenging. Poor cardinality estimates could result in the selection of bad plans by the query optimizer. Recently, deep learning has been applied to this problem with promising results. However, many of the proposed approaches often struggle to provide accurate results for multi attribute queries involving large number of predicates and with low selectivity.In this paper, we propose two complementary approaches that are effective for this scenario. Our first approach models selectivity estimation as a density estimation problem where one seeks to estimate the joint probability distribution from a finite number of samples. We leverage techniques from neural density estimation to build an accurate selectivity estimator. The key idea is to decompose the joint distribution into a set of tractable conditional probability distributions such that they satisfy the autoregressive property. Our second approach formulates selectivity estimation as a supervised deep learning problem that predicts the selectivity of a given query. We describe how to extend our algorithms for range queries. We also introduce and address a number of practical challenges arising when adapting deep learning for relational data. These include query/data featurization, incorporating

show abstract

“…With the development of DL techniques, entity matching [4,27], ontology alignment [25], and instance-level schema-matching [26] can utilize rich textual information to provide better solutions. However, both entity matching and instance-level schema matching assume the data can be queried on both sides, which can violate data privacy constraints.…”

Section: Related Workmentioning

confidence: 99%

SMAT: An Attention-Based Deep Learning Solution to the Automation of Schema Matching

Zhang

Shin

Choi

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Schema matching aims to identify the correspondences among attributes of database schemas. It is frequently considered as the most challenging and decisive stage existing in many contemporary web semantics and database systems. Low-quality algorithmic matchers fail to provide improvement while manually annotation consumes extensive human efforts. Further complications arise from data privacy in certain domains such as healthcare, where only schema level matching should be used to prevent data leakage. For this problem, we propose SMAT, a new deep learning model based on state-of-the-art natural language processing techniques to obtain semantic mappings between source and target schemas using only the attribute name and description. SMAT avoids directly encoding domain knowledge about the source and target systems, which allows it to be more easily deployed across different sites. We also introduce a new benchmark dataset, OMAP, based on real-world schema-level mappings from the healthcare domain. Our extensive evaluation of various benchmark datasets demonstrates the potential of SMAT to help automate schema-level matching tasks.

show abstract

Creating Embeddings of Heterogeneous Relational Datasets for Data Integration Tasks

Cited by 126 publications

References 15 publications

Merging Datasets of CyberSecurity Incidents for Fun and Insight

Merging Datasets of CyberSecurity Incidents for Fun and Insight

Deep Learning Models for Selectivity Estimation of Multi-Attribute Queries

SMAT: An Attention-Based Deep Learning Solution to the Automation of Schema Matching

Contact Info

Product

Resources

About