论文标题
SCORECAM GNN:UNE解释OptimaledesRéseauxprofonds sur图
ScoreCAM GNN: une explication optimale des réseaux profonds sur graphes
论文作者
论文摘要
深层网络的解释性正在成为深度学习社区中的核心问题。在图形上学习是相同的,这是许多现实世界中存在的数据结构。在本文中,我们提出了一种比最新方法更优化,更轻,一致且更好地利用评估图的拓扑结构的方法。
The explainability of deep networks is becoming a central issue in the deep learning community. It is the same for learning on graphs, a data structure present in many real world problems. In this paper, we propose a method that is more optimal, lighter, consistent and better exploits the topology of the evaluated graph than the state-of-the-art methods.