Posterior Label Smoothing for Node Classification
This work addresses node classification for graph data, but it is incremental as it adapts an existing regularization technique to a new domain.
The authors tackled the problem of node classification in graph-structured data by introducing posterior label smoothing, a method that derives soft labels from a posterior distribution based on neighborhood labels, resulting in consistent improvements in classification accuracy across 10 benchmark datasets.
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.