Design Requirements for Human-Centered Graph Neural Network Explanations

Pantea Habibi; Peyman Baghershahi; Sourav Medya; Debaleena Chattopadhyay

Design Requirements for Human-Centered Graph Neural Network Explanations

Machine Learning 2024-05-14 v1 Human-Computer Interaction

Authors: Pantea Habibi , Peyman Baghershahi , Sourav Medya , Debaleena Chattopadhyay

Abstract

Graph neural networks (GNNs) are powerful graph-based machine-learning models that are popular in various domains, e.g., social media, transportation, and drug discovery. However, owing to complex data representations, GNNs do not easily allow for human-intelligible explanations of their predictions, which can decrease trust in them as well as deter any collaboration opportunities between the AI expert and non-technical, domain expert. Here, we first discuss the two papers that aim to provide GNN explanations to domain experts in an accessible manner and then establish a set of design requirements for human-centered GNN explanations. Finally, we offer two example prototypes to demonstrate some of those proposed requirements.

Keywords

graph neural network graph convolutional network graph generation

Cite

@article{arxiv.2405.06917,
  title  = {Design Requirements for Human-Centered Graph Neural Network Explanations},
  author = {Pantea Habibi and Peyman Baghershahi and Sourav Medya and Debaleena Chattopadhyay},
  journal= {arXiv preprint arXiv:2405.06917},
  year   = {2024}
}

Design Requirements for Human-Centered Graph Neural Network Explanations

Abstract

Keywords

Cite

Related papers