NodeMixup: Tackling Under-Reaching for Graph Neural Networks
This addresses a specific bottleneck in GNNs for semi-supervised learning, offering an incremental improvement to enhance model performance in graph-based tasks.
The paper tackles the under-reaching issue in Graph Neural Networks (GNNs) for semi-supervised node classification, where uneven labeled node distribution limits accessibility to unlabeled nodes, and proposes NodeMixup, an architecture-agnostic method that improves performance by increasing labeled node reachability through mixup techniques, with extensive experiments demonstrating its efficacy.
Graph Neural Networks (GNNs) have become mainstream methods for solving the semi-supervised node classification problem. However, due to the uneven location distribution of labeled nodes in the graph, labeled nodes are only accessible to a small portion of unlabeled nodes, leading to the \emph{under-reaching} issue. In this study, we firstly reveal under-reaching by conducting an empirical investigation on various well-known graphs. Then, we demonstrate that under-reaching results in unsatisfactory distribution alignment between labeled and unlabeled nodes through systematic experimental analysis, significantly degrading GNNs' performance. To tackle under-reaching for GNNs, we propose an architecture-agnostic method dubbed NodeMixup. The fundamental idea is to (1) increase the reachability of labeled nodes by labeled-unlabeled pairs mixup, (2) leverage graph structures via fusing the neighbor connections of intra-class node pairs to improve performance gains of mixup, and (3) use neighbor label distribution similarity incorporating node degrees to determine sampling weights for node mixup. Extensive experiments demonstrate the efficacy of NodeMixup in assisting GNNs in handling under-reaching. The source code is available at \url{https://github.com/WeigangLu/NodeMixup}.