Optimization and Interpretability of Graph Attention Networks for Small Sparse Graph Structures in Automotive Applications

2023/05/25 by Marion Neumeier, Andreas Tollkühn, Neumeier, Marion +7 · 1 citation
Computer Science · Materials Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning in Materials Science

paper · pdf · doi:10.48550/arxiv.2305.16196

openalex publication_date 2023/05/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Assessing the Completeness of Traffic Scenario Categories for Automated Highway Driving Functions via Cluster-based Analysis

Related

• Causally-guided Regularization of Graph Attention Improves Generalizability
• Gradient Derivation for Learnable Parameters in Graph Attention Networks
• A Regularized Attention Mechanism for Graph Attention Networks
• Adaptive Depth Graph Attention Networks
• A Bird's-Eye Tutorial of Graph Attention Architectures