SAILOR: Structural Augmentation Based Tail Node Representation Learning

TL;DR

SAILOR enhances tail node representations in graph neural networks by jointly augmenting graph structure and learning more informative features, significantly improving performance on benchmark datasets.

Contribution

The paper introduces SAILOR, a novel framework that jointly learns to augment graph structure and improve tail node representations in GNNs.

Findings

SAILOR significantly outperforms existing methods on benchmark datasets.

Structural augmentation improves tail node representation quality.

Joint learning of structure and features enhances GNN expressiveness.

Abstract

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.