# A Structural-Clustering Based Active Learning for Graph Neural Networks

arXiv: https://arxiv.org/abs/2312.04307 · HTML: https://mlsanity.com/paper/2312.04307/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 7 Dec 2023.

## Builds on (most cited first, 7 of 7)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [A critical look at the evaluation of GNNs under heterophily: Are we really making progress?](https://mlsanity.com/paper/2302.11640/) (2023)
- [Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking](https://mlsanity.com/paper/1707.03815/) (2017)
- [Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networks](https://mlsanity.com/paper/2007.02901/) (2020)
- [Active Learning for Graph Neural Networks via Node Feature Propagation](https://mlsanity.com/paper/1910.07567/) (2019)
- [Partition-Based Active Learning for Graph Neural Networks](https://mlsanity.com/paper/2201.09391/) (2022)

## Built on by (most cited first, 1 of 1)

- [Robust Offline Active Learning on Graphs](https://mlsanity.com/paper/2408.07941/) (2024)

## Abstract (arXiv)

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.