Summary of Design Requirements For Human-centered Graph Neural Network Explanations, by Pantea Habibi et al.
Design Requirements for Human-Centered Graph Neural Network Explanations
by Pantea Habibi, Peyman Baghershahi, Sourav Medya, Debaleena Chattopadhyay
First submitted to arxiv on: 11 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper explores the challenge of providing human-intelligible explanations for graph neural network (GNN) predictions. Despite their popularity in domains like social media and drug discovery, GNNs lack transparency, making it difficult for domain experts to trust AI decisions and collaborate with them. The authors first review two papers that aim to provide GNN explanations and then propose a set of design requirements for human-centered GNN explanations. Two example prototypes are presented to demonstrate these proposed requirements. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary GNNs are powerful machine-learning models used in various fields, but they don’t explain their predictions well. This makes it hard for experts without technical knowledge to trust AI decisions and work with them. The paper talks about two other papers that try to make GNN explanations easier to understand. It also suggests what’s needed for good human-centered GNN explanations. Two examples are shown. |
Keywords
» Artificial intelligence » Gnn » Graph neural network » Machine learning
