2024/10/12 by Fangxin Wang, Wang, Fangxin, Kay Liu +5 · 1 citation
Computer Science · #Advanced Graph Neural Networks #Data Stream Mining Techniques #FOS: Computer and information sciences #Machine Learning (cs.LG) #Recommender Systems and Techniques #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.2410.09348
openalex publication_date 2024/10/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
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 .