Paper ID: 2406.04612

Revisiting Attention Weights as Interpretations of Message-Passing Neural Networks

Yong-Min Shin, Siqing Li, Xin Cao, Won-Yong Shin

The self-attention mechanism has been adopted in several widely-used message-passing neural networks (MPNNs) (e.g., GATs), which adaptively controls the amount of information that flows along the edges of the underlying graph. This usage of attention has made such models a baseline for studies on explainable AI (XAI) since interpretations via attention have been popularized in various domains (e.g., natural language processing and computer vision). However, existing studies often use naive calculations to derive attribution scores from attention, and do not take the precise and careful calculation of edge attribution into consideration. In our study, we aim to fill the gap between the widespread usage of attention-enabled MPNNs and their potential in largely under-explored explainability, a topic that has been actively investigated in other areas. To this end, as the first attempt, we formalize the problem of edge attribution from attention weights in GNNs. Then, we propose GATT, an edge attribution calculation method built upon the computation tree. Through comprehensive experiments, we demonstrate the effectiveness of our proposed method when evaluating attributions from GATs. Conversely, we empirically validate that simply averaging attention weights over graph attention layers is insufficient to interpret the GAT model's behavior. Code is publicly available at https://github.com/jordan7186/GAtt/tree/main.

Submitted: Jun 7, 2024