DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification

TL;DR

DiffusAL is a novel active graph learning method that combines multiple scoring functions, including graph diffusion heuristics, to efficiently select informative nodes for labeling, significantly outperforming random sampling across diverse datasets.

Contribution

We introduce DiffusAL, a robust, parameter-free active learning approach that integrates model uncertainty, diversity, and graph diffusion heuristics for improved node selection.

Findings

Outperforms random sampling on all benchmark datasets.

Efficient pre-processing enables faster acquisition and training.

Significantly improves label efficiency in node classification.

Abstract

Node classification is one of the core tasks on attributed graphs, but successful graph learning solutions require sufficiently labeled data. To keep annotation costs low, active graph learning focuses on selecting the most qualitative subset of nodes that maximizes label efficiency. However, deciding which heuristic is best suited for an unlabeled graph to increase label efficiency is a persistent challenge. Existing solutions either neglect aligning the learned model and the sampling method or focus only on limited selection aspects. They are thus sometimes worse or only equally good as random sampling. In this work, we introduce a novel active graph learning approach called DiffusAL, showing significant robustness in diverse settings. Toward better transferability between different graph structures, we combine three independent scoring functions to identify the most informative node samples for labeling in a parameter-free way: i) Model Uncertainty, ii) Diversity Component, and iii) Node Importance computed via graph diffusion heuristics. Most of our calculations for acquisition and training can be pre-processed, making DiffusAL more efficient compared to approaches combining diverse selection criteria and similarly fast as simpler heuristics. Our experiments on various benchmark datasets show that, unlike previous methods, our approach significantly outperforms random selection in 100% of all datasets and labeling budgets tested.