Posterior Label Smoothing for Node Classification

TL;DR

This paper introduces posterior label smoothing, a new regularization method for node classification on graphs that improves accuracy by adapting to graph structure and reducing overfitting.

Contribution

The paper proposes a novel posterior label smoothing technique that derives soft labels from neighborhood information, enhancing node classification across diverse graph types.

Findings

Consistent accuracy improvements on 10 benchmark datasets

Soft labels help mitigate overfitting during training

Pseudo-labeling refines global label statistics effectively

Abstract

Label smoothing is a widely studied regularization technique in machine learning. However, its potential for node classification in graph-structured data, spanning homophilic to heterophilic graphs, remains largely unexplored. We introduce posterior label smoothing, a novel method for transductive node classification that derives soft labels from a posterior distribution conditioned on neighborhood labels. The likelihood and prior distributions are estimated from the global statistics of the graph structure, allowing our approach to adapt naturally to various graph properties. We evaluate our method on 10 benchmark datasets using eight baseline models, demonstrating consistent improvements in classification accuracy. The following analysis demonstrates that soft labels mitigate overfitting during training, leading to better generalization performance, and that pseudo-labeling effectively refines the global label statistics of the graph. Our code is available at https://github.com/ml-postech/PosteL.