A Structural-Clustering Based Active Learning for Graph Neural Networks
This work addresses a domain-specific problem in graph neural networks for active learning, offering an incremental improvement over existing methods.
The paper tackles the underutilization of structural information in active learning for graph-structured data by proposing the Structural-Clustering PageRank method (SPA), which integrates community detection with PageRank scoring to select informative and central nodes, resulting in higher accuracy and macro-F1 scores across annotation budgets and reduced query time.
In active learning for graph-structured data, Graph Neural Networks (GNNs) have shown effectiveness. However, a common challenge in these applications is the underutilization of crucial structural information. To address this problem, we propose the Structural-Clustering PageRank method for improved Active learning (SPA) specifically designed for graph-structured data. SPA integrates community detection using the SCAN algorithm with the PageRank scoring method for efficient and informative sample selection. SPA prioritizes nodes that are not only informative but also central in structure. Through extensive experiments, SPA demonstrates higher accuracy and macro-F1 score over existing methods across different annotation budgets and achieves significant reductions in query time. In addition, the proposed method only adds two hyperparameters, $ε$ and $μ$ in the algorithm to finely tune the balance between structural learning and node selection. This simplicity is a key advantage in active learning scenarios, where extensive hyperparameter tuning is often impractical.