Learning Relational Representations with Auto-encoding Logic Programs

03/29/2019
by   Sebastijan Dumančić, et al.
0

Deep learning methods capable of handling relational data have proliferated over the last years. In contrast to traditional relational learning methods that leverage first-order logic for representing such data, these deep learning methods aim at re-representing symbolic relational data in Euclidean spaces. They offer better scalability, but can only numerically approximate relational structures and are less flexible in terms of reasoning tasks supported. This paper introduces a novel framework for relational representation learning that combines the best of both worlds. This framework, inspired by the auto-encoding principle, uses first-order logic as a data representation language, and the mapping between the original and latent representation is done by means of logic programs instead of neural networks. We show how learning can be cast as a constraint optimisation problem for which existing solvers can be used. The use of logic as a representation language makes the proposed framework more accurate (as the representation is exact, rather than approximate), more flexible, and more interpretable than deep learning methods. We experimentally show that these latent representations are indeed beneficial in relational learning tasks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/28/2016

Clustering-Based Relational Unsupervised Representation Learning with an Explicit Distributed Representation

The goal of unsupervised representation learning is to extract a new rep...
research
12/20/2013

Deep learning for neuroimaging: a validation study

Deep learning methods have recently made notable advances in the tasks o...
research
06/10/2020

Fitted Q-Learning for Relational Domains

We consider the problem of Approximate Dynamic Programming in relational...
research
02/06/2020

Relational Neural Machines

Deep learning has been shown to achieve impressive results in several ta...
research
08/02/2016

Relational Similarity Machines

This paper proposes Relational Similarity Machines (RSM): a fast, accura...
research
08/23/2023

Relational Concept Based Models

The design of interpretable deep learning models working in relational d...
research
04/10/2023

Scallop: A Language for Neurosymbolic Programming

We present Scallop, a language which combines the benefits of deep learn...

Please sign up or login with your details

Forgot password? Click here to reset