On Embeddings in Relational Databases

Arora, Siddhant; Bedathur, Srikanta

doi:10.48550/arxiv.2005.06437

Cited by 3 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In a real-life setting -tuples that are inserted via a query can be one of the following: (1) A hierarchy of materialized views -where each view can depend both on the DB and on previously defined views. (2) Tuples that are inserted via a SQL INSERT INTO SELECT statement. (3) Tuples that are inserted via a SQL UPDATE statement.…”

Section: Distant Lineagementioning

confidence: 99%

“…A naive implementation using semiring polynomials [19] requires saving the full provenance polynomial for each tuple, resulting in a massive growth in space consumption (for tuples that are produced by a query and that may depend on result tuples of previous queries). (2) Inductively built representations become very complex over time. Thus, they result in impractical provenance querying time.…”

Section: Motivationmentioning

confidence: 99%

“…Such a model is composed of a collection of real-valued vectors, each associated with a relevant DB term. The process of deriving vectors from DB-derived text is called relational embedding, which is a very active area of research [2,8,20].…”

Section: Word Vectors Modelmentioning

confidence: 99%

“…𝑇 𝑜𝑝 0.75 𝑇 𝑜𝑝 0.50 𝑇 𝑜𝑝 0.25 𝑇 𝑜𝑝 L[1] L[2] Experiment 2 query results vs. related materialized views (exp 2 , protein, sugars and unprepared).…”

mentioning

confidence: 99%

“…] L[2] L[3] L[4] 1.00 𝑇 𝑜𝑝 0.75 𝑇 𝑜𝑝 0.50 𝑇 𝑜𝑝 0.25 𝑇 𝑜𝑝 L[1] L[3] L[4] Experiment 3 query results vs. related base tables (products, nutrients and serving_size).…”

mentioning

confidence: 99%

See 4 more Smart Citations

ML Based Lineage in Databases

Leybovich,

Shmueli

2021

Preprint

View full text Add to dashboard Cite

We track the lineage of tuples throughout their database lifetime. That is, we consider a scenario in which tuples (records) that are produced by a query may affect other tuple insertions into the DB, as part of a normal workflow. As time goes on, exact provenance explanations for such tuples become deeply nested, increasingly consuming space, and resulting in decreased clarity and readability.We present a novel approach for approximating lineage tracking, using a Machine Learning (ML) and Natural Language Processing (NLP) technique; namely, word embedding. The basic idea is summarizing (and approximating) the lineage of each tuple via a small set of constant-size vectors (the number of vectors per-tuple is a hyperparameter). For explicitly (and independently of DB contents) inserted tuples -the vectors are obtained via a pre-trained word vectors model over their underlying database domain "text". During the execution of a query, we construct the lineage vectors of the final (and intermediate) result tuples in a similar fashion to that of semiring-based exact provenance calculations. We extend the + and • operations to generate sets of lineage vectors, while retaining the ability to propagate information and preserve the compact representation. Therefore, our solution does not suffer from space complexity blow-up over time, and it "naturally ranks" explanations to the existence of a tuple.We devise a genetics-inspired improvement to our basic method. The data columns of an entity (and potentially other columns) are a tuple's basic properties, i.e., the "genes" that combine to form its genetic code. We design an alternative lineage tracking mechanism, that of keeping track of and querying lineage (via embeddings) at the column ("gene") level; thereby, we manage to better distinguish between the provenance features and the textual characteristics of a tuple. Finding the lineage of a tuple in the DB is analogous to finding its predecessors via DNA examination.We further introduce several improvements and extensions to the basic method: tuple creation timestamp, column emphasis and query dependency DAG.We integrate our lineage computations into the PostgreSQL system via an extension (ProvSQL) and extensive experiments exhibit useful results in terms of accuracy against exact, semiring-based, justifications, especially for the column-based (CV) method which exhibits high precision and high per-level recall. In the experiments, we focus on tuples with multiple generations of tuples in their lifelong lineage and analyze them in terms of direct and distant lineage.

show abstract

Section: Distant Lineagementioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

Section: Word Vectors Modelmentioning

confidence: 99%

“…𝑇 𝑜𝑝 0.75 𝑇 𝑜𝑝 0.50 𝑇 𝑜𝑝 0.25 𝑇 𝑜𝑝 L[1] L[2] Experiment 2 query results vs. related materialized views (exp 2 , protein, sugars and unprepared).…”

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

ML Based Lineage in Databases

Leybovich,

Shmueli

2021

Preprint

View full text Add to dashboard Cite

show abstract

Towards practical approximate lineage

Leybovich

Shmueli

2022

Proceedings of the 14th International Workshop on the Theory and Practice of Provenance

View full text Add to dashboard Cite

Traditionally, provenance and lineage mainly referred to query results. We take a more holistic approach. We consider a system in which tuples (records) that are produced by a query may affect other tuple insertions into the DB, as part of a normal workflow. Therefore, we consider both direct lineage (dependence of a query result on database tuples directly used in solving the query) and distant lineage (dependence on older tuples that caused the existence

show abstract

DrugDBEmbed : Semantic Queries on Relational Database using Supervised Column Encodings

Bandyopadhyay,

Maneriker,

Patel

et al. 2020

Preprint

View full text Add to dashboard Cite

Traditional relational databases contain a lot of latent semantic information that have largely remained untapped due to the difficulty involved in automatically extracting such information. Recent works have proposed unsupervised machine learning approaches to extract such hidden information by textifying the database columns and then projecting the text tokens onto a fixed dimensional semantic vector space. However, in certain databases, task-specific class labels may be available, which unsupervised approaches are unable to lever in a principled manner. Also, when embeddings are generated at individual token level, then column encoding of multitoken text column has to be computed by taking the average of the vectors of the tokens present in that column for any given row. Such averaging approach may not produce the best semantic vector representation of the multi-token text column, as observed while encoding paragraphs or documents in natural language processing domain. With these shortcomings in mind, we propose a supervised machine learning approach using a Bi-LSTM based sequence encoder to directly generate column encodings for multi-token text columns of the DrugBank database, which contains gold standard drug-drug interaction (DDI) labels. Our text data driven encoding approach achieves very high Accuracy on the supervised DDI prediction task for some columns and we use those supervised column encodings to simulate and evaluate the Analogy SQL queries on relational data to demonstrate the efficacy of our technique.

show abstract

On Embeddings in Relational Databases

Cited by 3 publications

References 0 publications

ML Based Lineage in Databases

ML Based Lineage in Databases

Towards practical approximate lineage

DrugDBEmbed : Semantic Queries on Relational Database using Supervised Column Encodings

Contact Info

Product

Resources

About