A Structural-Clustering Based Active Learning for Graph Neural Networks

2023/12/07 by Ricky Maulana Fajri, Yulong Pei, Fajri, Ricky Maulana +5
Computer Science · Materials Science · #Advanced Graph Neural Networks #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Algorithms #Machine Learning in Materials Science

paper · pdf · doi:10.48550/arxiv.2312.04307

openalex publication_date 2023/12/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Related

• Partition-Based Active Learning for Graph Neural Networks
• Active Learning for Graph Neural Networks via Node Feature Propagation
• Data Skeleton Learning: Scalable Active Clustering with Sparse Graph Structures
• Class-Balanced and Reinforced Active Learning on Graphs
• Research on the application of graph data structure and graph neural network in node classification/clustering tasks