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

Paul Cibier, Jean-Guy Mailly
4/29/2024
cs.AI

No official code found. Best implementation: Paulo-21/AF-GCN-GAT_wGS (1 star, Rust, last commit 2025-02-23).

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.

View on arXivView PDF

Code Implementations(1)

Paulo-21/AF-GCN-GAT_wGSCommunity56%
Rust

Repo of the paper https://arxiv.org/pdf/2404.18672

10Rust, PythonJun 12, 20241 years ago

Similar Papers

Neuro-Argumentative Learning with Case-Based Reasoning

81% match1 repo32025

ArgU: A Controllable Factual Argument Generator

80% match2023

Towards Unified Neurosymbolic Reasoning on Knowledge Graphs

80% match2025

Untrained neural networks can demonstrate memorization-independent abstract reasoning

80% match2024

Compositional Attention Networks for Machine Reasoning

80% match1 repo5092018

ONNXExplainer: an ONNX Based Generic Framework to Explain Neural Networks Using Shapley Values

80% match2023

Cite this paper

@article{cibier2024graph,
  title  = {Graph Convolutional Networks and Graph Attention Networks for Approximating Arguments Acceptability -- Technical Report},
  author = {Paul Cibier and Jean-Guy Mailly},
  year   = {2024},
  eprint = {2404.18672},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.18672v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.18672.svg)](https://codeofpaper.com/paper/2404.18672)

Discussion