Learning Representations for Sub-Symbolic Reasoning

by   Giuseppe Marra, et al.

Neuro-symbolic methods integrate neural architectures, knowledge representation and reasoning. However, they have been struggling at both dealing with the intrinsic uncertainty of the observations and scaling to real world applications. This paper presents Relational Reasoning Networks (R2N), a novel end-to-end model that performs relational reasoning in the latent space of a deep learner architecture, where the representations of constants, ground atoms and their manipulations are learned in an integrated fashion. Unlike flat architectures like Knowledge Graph Embedders, which can only represent relations between entities, R2Ns define an additional computational structure, accounting for higher-level relations among the ground atoms. The considered relations can be explicitly known, like the ones defined by logic formulas, or defined as unconstrained correlations among groups of ground atoms. R2Ns can be applied to purely symbolic tasks or as a neuro-symbolic platform to integrate learning and reasoning in heterogeneous problems with both symbolic and feature-based represented entities. The proposed model bridges the gap between previous neuro-symbolic methods that have been either limited in terms of scalability or expressivity. The proposed methodology is shown to achieve state-of-the-art results in different experimental settings.


page 1

page 2

page 3

page 4


pix2rule: End-to-end Neuro-symbolic Rule Learning

Humans have the ability to seamlessly combine low-level visual input wit...

Modeling Content and Context with Deep Relational Learning

Building models for realistic natural language tasks requires dealing wi...

Dealing with Uncertainty in Situation Assessment: towards a Symbolic Approach

The situation assessment problem is considered, in terms of object, cond...

Logical Interpretations of Autoencoders

The unification of low-level perception and high-level reasoning is a lo...

TexRel: a Green Family of Datasets for Emergent Communications on Relations

We propose a new dataset TexRel as a playground for the study of emergen...

An Explicitly Relational Neural Network Architecture

With a view to bridging the gap between deep learning and symbolic AI, w...

LYRICS: a General Interface Layer to Integrate AI and Deep Learning

In spite of the amazing results obtained by deep learning in many applic...