Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning

• Main Authors: Luo, Yuankai, Li, Hongkang, Liu, Qijiong, Shi, Lei, Wu, Xiao-Ming
• Format: Journal Article
• Language: English
• Published: 26-05-2024
• Subjects: Computer Science - Learning
• DOI: 10.48550/arxiv.2405.16435

We present a novel end-to-end framework that generates highly compact
(typically 6-15 dimensions), discrete (int4 type), and interpretable node
representations, termed node identifiers (node IDs), to tackle inference
challenges on large-scale graphs. By employing vector quantization, we compress
continuous node embeddings from multiple layers of a Graph Neural Network (GNN)
into discrete codes, applicable under both self-supervised and supervised
learning paradigms. These node IDs capture high-level abstractions of graph
data and offer interpretability that traditional GNN embeddings lack. Extensive
experiments on 34 datasets, encompassing node classification, graph
classification, link prediction, and attributed graph clustering tasks,
demonstrate that the generated node IDs significantly enhance speed and memory
efficiency while achieving competitive performance compared to current
state-of-the-art methods.