BANGS: Game-Theoretic Node Selection for Graph Self-Training
Abstract
Graph self-training is a semi-supervised learning method that iteratively selects a set of unlabeled data to retrain the underlying graph neural network (GNN) model and improve its prediction performance. While selecting highly confident nodes has proven effective for self-training, this pseudo-labeling strategy ignores the combinatorial dependencies between nodes and suffers from a local view of the distribution. To overcome these issues, we propose BANGS, a novel framework that unifies the labeling strategy with conditional mutual information as the objective of node selection. Our approach -- grounded in game theory -- selects nodes in a combinatorial fashion and provides theoretical guarantees for robustness under noisy objective. More specifically, unlike traditional methods that rank and select nodes independently, BANGS considers nodes as a collective set in the self-training process. Our method demonstrates superior performance and robustness across various datasets, base models, and hyperparameter settings, outperforming existing techniques. The codebase is available on https://github.com/fangxin-wang/BANGS .
Cite
@article{arxiv.2410.09348,
title = {BANGS: Game-Theoretic Node Selection for Graph Self-Training},
author = {Fangxin Wang and Kay Liu and Sourav Medya and Philip S. Yu},
journal= {arXiv preprint arXiv:2410.09348},
year = {2024}
}
Comments
Preprint