English

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

Machine Learning 2023-10-03 v1 Social and Information Networks

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.

Keywords

Cite

@article{arxiv.2308.00146,
  title  = {DiffusAL: Coupling Active Learning with Graph Diffusion for Label-Efficient Node Classification},
  author = {Sandra Gilhuber and Julian Busch and Daniel Rotthues and Christian M. M. Frey and Thomas Seidl},
  journal= {arXiv preprint arXiv:2308.00146},
  year   = {2023}
}

Comments

Accepted @ ECML PKDD 2023. This is the author's version of the work. The definitive Version of Record will be published in the Proceedings of ECML PKDD 2023