Interactive join query inference with JIM

Bonifati, Angela; Ciucanu, Radu; Staworko, Sławek

doi:10.14778/2733004.2733025

Cited by 14 publications

(17 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our work [11,12], we have studied the following setting: the input instance consists of a collection of relations (that can be viewed as a unique denormalized table corresponding to their Cartesian product), the fragments are individual tuples from that instance, and the goal query class consists of the set of all join predicates that can be formulated over it.…”

Section: Learning Relational Queriesmentioning

confidence: 99%

“…becomes "Labeling which tuple allows us to eliminate as many elements of the lattice as possible?" Finally, we point out that we have implemented the proposed strategies in Jim (Join Inference Machine) [12], a system that can learn arbitrary n-ary join predicates, spanning from relational tables to sets of tagged images.…”

Section: Learning Relational Queriesmentioning

confidence: 99%

“…For the validation of our paradigm [10,11,12], we have considered the simplest possible user input by requiring the user only to answer Yes or No to simple fragment labeling. This type of interactions is inspired by the well-known framework of learning with membership queries proposed by Angluin [6].…”

Section: Related Workmentioning

confidence: 99%

“…The instantiation of our paradigm for learning relational queries [11,12] follows a very recent line of research [39,34,18] from which we differ in two ways: (i) we assume no knowledge of the database schema, and (ii) we do not have an initial query output to start with and we discover it from user interactions. Another work strongly related to ours is [1,2], which focuses on learning quantified Boolean queries and also uses the framework of learning with membership queries [6].…”

Section: Related Workmentioning

confidence: 99%

“…Then, we point out that we have validated two instantiations of the paradigm for learning relational join queries [11,12] and for learning graph queries [10]; we briefly present our results on these two application settings in Section 3 and Section 4, respectively. We discuss related work in Section 5.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A Paradigm for Learning Queries on Big Data

Bonifati

Ciucanu

Lemay

et al. 2014

Proceedings of the First International Workshop on Bringing the Value of "Big Data" to Users (Data4U 2014)

Self Cite

View full text Add to dashboard Cite

International audienceSpecifying a database query using a formal query language is typically a challenging task for non-expert users. In the context of big data, this problem becomes even harder as it requires the users to deal with database instances of big sizes and hence difficult to visualize. Such instances usually lack a schema to help the users specify their queries, or have an incomplete schema as they come from disparate data sources. In this paper, we propose a novel paradigm for interactive learning of queries on big data, without assuming any knowledge of the database schema. The paradigm can be applied to different database models and a class of queries adequate to the database model. In particular, in this paper we present two instantiations that validated the proposed paradigm for learning relational join queries and for learning path queries on graph databases. Finally, we discuss the challenges of employing the paradigm for further data models and for learning cross-model schema mappings

show abstract

Section: Learning Relational Queriesmentioning

confidence: 99%

Section: Learning Relational Queriesmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Paradigm for Learning Queries on Big Data

Bonifati

Ciucanu

Lemay

et al. 2014

Proceedings of the First International Workshop on Bringing the Value of "Big Data" to Users (Data4U 2014)

Self Cite

View full text Add to dashboard Cite

show abstract

A First Experimental Study on Functional Dependencies for Imbalanced Datasets Classification

Guilly

Petit

Scuturici

2019

Communications in Computer and Information Science

View full text Add to dashboard Cite

Imbalanced datasets for classification is a recurring problem in machine learning, as most real-life datasets present classes that are not evenly distributed. This causes many problems for classification algorithms trained on such datasets, as they are often biases towards the majority class. Moreover, the minority class often yields more interest for data scientist, when at the same time it is also the hardest to predict. Many different approaches have been proposed to tackle the problem of imbalanced datasets: they often rely on the sampling of the majority class, or the creation of synthetic examples for the minority one. In this paper, we take a completely different perspective on this problem: we propose to use the notion of distance between databases, to sample from the majority class, so that the minority and majority class are as distant as possible. The chosen distance is based on functional dependencies, with the intuition of capturing inherent constraints of the database. We propose algorithms to generate distant synthetic datasets, as well as experimentations to verify our conjecture on the classification on distant instances. Despite the mitigated results obtained so far, we believe this is a promising research direction, at the intersection of machine learning and databases, and it deserves more investigations.

show abstract