SAILOR: Structural Augmentation Based Tail Node Representation Learning
This addresses a specific bottleneck in graph representation learning for real-world graphs with many low-degree nodes, offering a targeted improvement.
The paper tackles the problem of Graph Neural Networks (GNNs) producing inferior representations for tail nodes in graphs with long-tailed degree distributions, and proposes SAILOR, a framework that improves tail node representations and outperforms state-of-the-art baselines in experiments.
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in representation learning for graphs recently. However, the effectiveness of GNNs, which capitalize on the key operation of message propagation, highly depends on the quality of the topology structure. Most of the graphs in real-world scenarios follow a long-tailed distribution on their node degrees, that is, a vast majority of the nodes in the graph are tail nodes with only a few connected edges. GNNs produce inferior node representations for tail nodes since they lack structural information. In the pursuit of promoting the expressiveness of GNNs for tail nodes, we explore how the deficiency of structural information deteriorates the performance of tail nodes and propose a general Structural Augmentation based taIL nOde Representation learning framework, dubbed as SAILOR, which can jointly learn to augment the graph structure and extract more informative representations for tail nodes. Extensive experiments on public benchmark datasets demonstrate that SAILOR can significantly improve the tail node representations and outperform the state-of-the-art baselines.