用谱编码提升异构图注意力模型性能
Graph Attention for Heterogeneous Graphs with Positional Encoding
- 引入全拉普拉斯谱编码节点位置信息
- 在节点分类与链接预测上显著提升准确率
- 适合研究异构图表示学习的学者参考
图神经网络（GNN）已成为建模图数据的标准方法，注意力机制和Transformer显著提升了其在图任务中的表现。尽管如此，现有GNN在异构图上的性能仍普遍低于同构图。本文系统评估多种GNN架构，聚焦节点分类与链接预测任务，发现图注意力网络（GAT）表现最优。核心贡献在于将节点位置编码融入注意力机制，利用全拉普拉斯谱精确捕捉节点的相对与绝对位置，进一步提升下游任务如节点分类与链接预测的性能。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have emerged as the de facto standard for modeling graph data, with attention mechanisms and transformers significantly enhancing their performance on graph-based tasks. Despite these advancements, the performance of GNNs on heterogeneous graphs often remains complex, with networks generally underperforming compared to their homogeneous counterparts. This work benchmarks various GNN architectures to identify the most effective methods for heterogeneous graphs, with a particular focus on node classification and link prediction. Our findings reveal that graph attention networks excel in these tasks. As a main contribution, we explore enhancements to these attention networks by integrating positional encodings for node embeddings. This involves utilizing the full Laplacian spectrum to accurately capture both the relative and absolute positions of each node within the graph, further enhancing performance on downstream tasks such as node classification and link prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。