DeepAI
Log In Sign Up

Interpreting Neural Networks as Gradual Argumentation Frameworks (Including Proof Appendix)

12/10/2020
by   Nico Potyka, et al.
0

We show that an interesting class of feed-forward neural networks can be understood as quantitative argumentation frameworks. This connection creates a bridge between research in Formal Argumentation and Machine Learning. We generalize the semantics of feed-forward neural networks to acyclic graphs and study the resulting computational and semantical properties in argumentation graphs. As it turns out, the semantics gives stronger guarantees than existing semantics that have been tailor-made for the argumentation setting. From a machine-learning perspective, the connection does not seem immediately helpful. While it gives intuitive meaning to some feed-forward-neural networks, they remain difficult to understand due to their size and density. However, the connection seems helpful for combining background knowledge in form of sparse argumentation networks with dense neural networks that have been trained for complementary purposes and for learning the parameters of quantitative argumentation frameworks in an end-to-end fashion from data.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/26/2021

Relational Argumentation Semantics

In this paper, we propose a fresh perspective on argumentation semantics...
07/01/2021

Visualising Argumentation Graphs with Graph Embeddings and t-SNE

This paper applies t-SNE, a visualisation technique familiar from Deep N...
06/25/2021

Learning Gradual Argumentation Frameworks using Genetic Algorithms

Gradual argumentation frameworks represent arguments and their relations...
01/16/2014

On the Intertranslatability of Argumentation Semantics

Translations between different nonmonotonic formalisms always have been ...
11/25/2016

Bipolar Weighted Argumentation Graphs

This paper discusses the semantics of weighted argumentation graphs that...
10/30/2017

A Connection between Feed-Forward Neural Networks and Probabilistic Graphical Models

Two of the most popular modelling paradigms in computer vision are feed-...
06/30/2019

Multilingual Bottleneck Features for Query by Example Spoken Term Detection

State of the art solutions to query by example spoken term detection (Qb...