.png){kind=icon}
.png){kind=icon}
Return
A graph convolutional network-based solver for approximating argument acceptability
.png){kind=icon}
OA
AI
DOI：10.1016/j.softx.2025.102434.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
AFGCN is a software tool for approximate solutions to abstract argumentation using a Graph Convolutional Network (GCN). It addresses the computational complexity of determining argument acceptability across several semantics. The model incorporates deep residual connections, randomized training, and groundedreasoning features to achieve strong approximation accuracy. The solver predicts acceptability status for credulous and skeptical tasks. Leveraging graph-based learning and an optimized runtime, AFGCN provides an efficient and scalable method for large-scale argumentation frameworks.
Keywords:
Abstract argumentation
Graph convolutional networks
Approximate reasoning
Argument acceptability
ICCMA
Graph neural networks
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.