Graph Convolutional Networks and Graph Attention Networks for Approximating Arguments Acceptability -- Technical Report

TL;DR

This paper enhances neural network methods for abstract argumentation by improving Graph Convolutional Networks (GCNs) and introducing Graph Attention Networks (GATs) to boost efficiency and accuracy.

Contribution

It advances the state-of-the-art by improving GCN performance and proposing GATs for better efficiency in argument acceptability tasks.

Findings

Improved GCN performance in runtime and accuracy.

GAT architecture further enhances efficiency.

Neural network approaches effectively address argumentation decision problems.

Abstract

Various approaches have been proposed for providing efficient computational approaches for abstract argumentation. Among them, neural networks have permitted to solve various decision problems, notably related to arguments (credulous or skeptical) acceptability. In this work, we push further this study in various ways. First, relying on the state-of-the-art approach AFGCN, we show how we can improve the performances of the Graph Convolutional Networks (GCNs) regarding both runtime and accuracy. Then, we show that it is possible to improve even more the efficiency of the approach by modifying the architecture of the network, using Graph Attention Networks (GATs) instead.