ALINC aggregates node-level active learning utilities to graph-level selection criteria and benchmarks ten strategies across three aggregation methods on four datasets, identifying CoreSet, TypiClust, and BADGE as top performers.
arXiv preprint arXiv:1910.07567 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
CANE estimates cluster-specific reliability of noisy LLM pseudo-labels on graphs without ground truth to improve label-free node classification.
Active learning with randomly initialized models achieves comparable results to traditional candidate-model methods, with low-confidence sampling proving most effective.
citing papers explorer
-
ALINC: Active Learning for Inductive Node Classification via Graph Sampling
ALINC aggregates node-level active learning utilities to graph-level selection criteria and benchmarks ten strategies across three aggregation methods on four datasets, identifying CoreSet, TypiClust, and BADGE as top performers.
-
Where LLM Annotators Fail: Label-Free Learning on Graphs with LLMs
CANE estimates cluster-specific reliability of noisy LLM pseudo-labels on graphs without ground truth to improve label-free node classification.