Deep Models for Relational Databases

03/21/2019
by   Devon Graham, et al.
0

Due to its extensive use in databases, the relational model is ubiquitous in representing big-data. We propose to apply deep learning to this type of relational data by introducing an Equivariant Relational Layer (ERL), a neural network layer derived from the entity-relationship model of the database. Our layer relies on identification of exchangeabilities in the relational data(base), and their expression as a permutation group. We prove that an ERL is an optimal parameter-sharing scheme under the given exchangeability constraints, and subsumes recently introduced deep models for sets, exchangeable tensors, and graphs. The proposed model has a linear complexity in the size of the relational data, and it can be used for both inductive and transductive reasoning in databases, including the prediction of missing records, and database embedding. This opens the door to the application of deep learning to one of the most abundant forms of data.

READ FULL TEXT

page 6

page 9

research
03/20/2013

From Relational Databases to Belief Networks

The relationship between belief networks and relational databases is exa...
research
01/25/2022

Serving Deep Learning Models with Deduplication from Relational Databases

There are significant benefits to serve deep learning models from relati...
research
02/24/2020

Symbolic Querying of Vector Spaces: Probabilistic Databases Meets Relational Embeddings

To deal with increasing amounts of uncertainty and incompleteness in rel...
research
01/24/2019

HRDBMS: Combining the Best of Modern and Traditional Relational Databases

HRDBMS is a novel distributed relational database that uses a hybrid mod...
research
05/31/2019

Knowledge-augmented Column Networks: Guiding Deep Learning with Advice

Recently, deep models have had considerable success in several tasks, es...
research
11/04/2022

Neural RELAGGS

Multi-relational databases are the basis of most consolidated data colle...
research
09/20/2023

Relational Expressions for Data Transformation and Computation

Separate programming models for data transformation (declarative) and co...

Please sign up or login with your details

Forgot password? Click here to reset