Skip to content
Back to skills

Faithful And Accurate Selfattention Attribution For Message Passing Neural Networks Via The Computation Tree Viewpoint

ASecurity

**arXiv ID:** 2406.04612 **Authors:** Yong-Min Shin, Siqing Li, Xin Cao, Won-Yong Shin **Published:** 2024-06-07T03:40:15Z **Abstract:** The self-attention mechanism has been adopted in various popular message passing neural networks (MPNNs), enabling the model to adaptively control the amount of information that flows along the edges of the underlying graph. Such attention-based MPNNs (Att-GNNs) have also been used as a baseline for multiple studies on explainable AI (XAI) since attention ha...

  • 3 stars
  • 0 votes
  • 0 copies
  • 6 views
  • Added September 11, 2026
toolsgit

Security analysis

A100/100

Scanned September 11, 2026

npx -y skills add hiyenwong/ai_collection --skill faithful-and-accurate-selfattention-attribution-for-message-passing-neural-networks-via-the-computation-tree-viewpoint --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Faithful And Accurate Selfattention Attribution For Message Passing Neural Networks Via The Computation Tree Viewpoint?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Faithful And Accurate Selfattention Attribution For Message Passing Neural Networks Via The Computation Tree Viewpoint
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hiyenwong-faithful-and-accurate-selfattention-attribution-fo/badge)](https://www.skillsdirectory.com/skills/hiyenwong-faithful-and-accurate-selfattention-attribution-fo)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
# Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint

**arXiv ID:** 2406.04612
**Authors:** Yong-Min Shin, Siqing Li, Xin Cao, Won-Yong Shin
**Published:** 2024-06-07T03:40:15Z
**Abstract:**
The self-attention mechanism has been adopted in various popular message passing neural networks (MPNNs), enabling the model to adaptively control the amount of information that flows along the edges of the underlying graph. Such attention-based MPNNs (Att-GNNs) have also been used as a baseline for multiple studies on explainable AI (XAI) since attention has steadily been seen as natural model interpretations, while being a viewpoint that has already been popularized in other domains (e.g., natural language processing and computer vision). However, existing studies often use naive calculations to derive attribution scores from attention, undermining the potential of attention as interpretations for Att-GNNs. In our study, we aim to fill the gap between the widespread usage of Att-GNNs and their potential explainability via attention. To this end, we propose GATT, edge attribution calculation method for self-attention MPNNs based on the computation tree, a rooted tree that reflects the computation process of the underlying model. Despite its simplicity, we empirically demonstrate the effectiveness of GATT in three aspects of model explanation: faithfulness, explanation accuracy, and case studies by using both synthetic and real-world benchmark datasets. In all cases, the results demonstrate that GATT greatly improves edge attribution scores, especially compared to the previous naive approach. Our code is available at https://github.com/jordan7186/GAtt.

## Skill Description

This skill is generated from the arXiv paper: Faithful and Accurate Self-Attention Attribution for Message Passing Neural Networks via the Computation Tree Viewpoint (2406.04612).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2406.04612](http://arxiv.org/abs/2406.04612v2)

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in tools →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.