Leveraging Label Non-Uniformity for Node Classification in Graph Neural Networks

TL;DR

This paper reveals how label non-uniformity in GNNs can be exploited to infer graph structure and improve node classification accuracy by adjusting training data and graph topology.

Contribution

It introduces the concept of label non-uniformity derived from Wasserstein distance and demonstrates how manipulating it enhances GNN performance.

Findings

Nodes with low label non-uniformity are harder to classify.

Increasing high non-uniformity samples improves accuracy.

Edge dropping reduces cut size and boosts performance.

Abstract

In node classification using graph neural networks (GNNs), a typical model generates logits for different class labels at each node. A softmax layer often outputs a label prediction based on the largest logit. We demonstrate that it is possible to infer hidden graph structural information from the dataset using these logits. We introduce the key notion of label non-uniformity, which is derived from the Wasserstein distance between the softmax distribution of the logits and the uniform distribution. We demonstrate that nodes with small label non-uniformity are harder to classify correctly. We theoretically analyze how the label non-uniformity varies across the graph, which provides insights into boosting the model performance: increasing training samples with high non-uniformity or dropping edges to reduce the maximal cut size of the node set of small non-uniformity. These mechanisms can be easily added to a base GNN model. Experimental results demonstrate that our approach improves the performance of many benchmark base models.