KR2020Proceedings of the 17th International Conference on Principles of Knowledge Representation and ReasoningProceedings of the 17th International Conference on Principles of Knowledge Representation and Reasoning

Rhodes, Greece. September 12-18, 2020.

Edited by

ISSN: 2334-1033
ISBN: 978-0-9992411-7-2

Sponsored by
Published by

Copyright © 2020 International Joint Conferences on Artificial Intelligence Organization

Neuro-Symbolic Probabilistic Argumentation Machines

  1. Regis Riveret(The Commonwealth Scientific and Industrial Research Organisation, Australia)
  2. Son Tran(University of Tasmania, Australia)
  3. Artur d'Avila Garcez(City, University of London, United Kingdom)

Keywords

  1. Explainable AI-General
  2. Graphical models for knowledge representation and reasoning-
  3. Neural-symbolic learning-General
  4. Probabilistic reasoning and learning-General

Abstract

Neural-symbolic systems combine the strengths of neural networks and symbolic formalisms. In this paper, we introduce a neural-symbolic system which combines restricted Boltzmann machines and probabilistic semi-abstract argumentation. We propose to train networks on argument labellings explaining the data, so that any sampled data outcome is associated with an argument labelling. Argument labellings are integrated as constraints within restricted Boltzmann machines, so that the neural networks are used to learn probabilistic dependencies amongst argument labels. Given a dataset and an argumentation graph as prior knowledge, for every example/case K in the dataset, we use a so-called K-maxconsistent labelling of the graph, and an explanation of case K refers to a K-maxconsistent labelling of the given argumentation graph. The abilities of the proposed system to predict correct labellings were evaluated and compared with standard machine learning techniques. Experiments revealed that such argumentation Boltzmann machines can outperform other classification models, especially in noisy settings.