Log In Sign Up

Deep Learning for Abstract Argumentation Semantics

by   Dennis Craandijk, et al.

In this paper, we present a learning-based approach to determining acceptance of arguments under several abstract argumentation semantics. More specifically, we propose an argumentation graph neural network (AGNN) that learns a message-passing algorithm to predict the likelihood of an argument being accepted. The experimental results demonstrate that the AGNN can almost perfectly predict the acceptability under different semantics and scales well for larger argumentation frameworks. Furthermore, analysing the behaviour of the message-passing algorithm shows that the AGNN learns to adhere to basic principles of argument semantics as identified in the literature, and can thus be trained to predict extensions under the different semantics - we show how the latter can be done for multi-extension semantics by using AGNNs to guide a basic search. We publish our code at


page 1

page 2

page 3

page 4


Necessary and Sufficient Explanations in Abstract Argumentation

In this paper, we discuss necessary and sufficient explanations for form...

The Inverse Problem for Argumentation Gradual Semantics

Gradual semantics with abstract argumentation provide each argument with...

Some Supplementaries to The Counting Semantics for Abstract Argumentation

Dung's abstract argumentation framework consists of a set of interacting...

Learning Gradual Argumentation Frameworks using Genetic Algorithms

Gradual argumentation frameworks represent arguments and their relations...

Analytical Solutions for the Inverse Problem within Gradual Semantics

Gradual semantics within abstract argumentation associate a numeric scor...

Compact Argumentation Frameworks

Abstract argumentation frameworks (AFs) are one of the most studied form...