Nonlinear Correct and Smooth for Semi-Supervised Learning
This work addresses a domain-specific problem in graph-based semi-supervised learning for researchers and practitioners, offering incremental improvements by enhancing existing post-processing methods.
The paper tackles the problem of improving graph-based semi-supervised learning by proposing Nonlinear Correct and Smooth (NLCS), which incorporates non-linearity and higher-order representation into residual propagation, achieving average improvements of 13.71% over base prediction and 2.16% over the state-of-the-art post-processing method on six datasets.
Graph-based semi-supervised learning (GSSL) has been used successfully in various applications. Existing methods leverage the graph structure and labeled samples for classification. Label Propagation (LP) and Graph Neural Networks (GNNs) both iteratively pass messages on graphs, where LP propagates node labels through edges and GNN aggregates node features from the neighborhood. Recently, combining LP and GNN has led to improved performance. However, utilizing labels and features jointly in higher-order graphs has not been explored. Therefore, we propose Nonlinear Correct and Smooth (NLCS), which improves the existing post-processing approach by incorporating non-linearity and higher-order representation into the residual propagation to handle intricate node relationships effectively. Systematic evaluations show that our method achieves remarkable average improvements of 13.71% over base prediction and 2.16% over the state-of-the-art post-processing method on six commonly used datasets. Comparisons and analyses show our method effectively utilizes labels and features jointly in higher-order graphs to resolve challenging graph relationships.