For automotive applications, the Graph Attention Network (GAT) is a prominently used architecture to include relational information of a traffic scenario during feature embedding. As shown in this work, however, one of the most popular GAT realizations, namely GATv2, has potential pitfalls that hinder an optimal parameter learning. Especially for small and sparse graph structures a proper optimization is problematic. To surpass limitations, this work proposes architectural modifications of GATv2. In controlled experiments, it is shown that the proposed model adaptions improve prediction performance in a node-level regression task and make it more robust to parameter initialization. This work aims for a better understanding of the attention mechanism and analyzes its interpretability of identifying causal importance.

翻译：针对汽车应用场景，图注意力网络(GAT)是一种在特征嵌入过程中融合交通场景关系信息的典型架构。然而本研究表明，最流行的GAT实现之一——GATv2——存在阻碍最优参数学习的潜在缺陷，尤其在小规模稀疏图结构上难以实现有效优化。为突破上述局限，本研究提出对GATv2的架构改进。通过控制变量实验证明，所提出的模型改进方案在节点级回归任务中提升了预测性能，并增强了参数初始化的鲁棒性。本研究旨在深入理解注意力机制，并分析其在识别因果重要性方面的可解释性。