ADC-GNN improves few-shot graph fraud detection by combining diffusion-guided feature augmentation, contrastive learning, and multi-hop spectral attention, showing gains on public benchmarks under 1% labeled data.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection
ADC-GNN improves few-shot graph fraud detection by combining diffusion-guided feature augmentation, contrastive learning, and multi-hop spectral attention, showing gains on public benchmarks under 1% labeled data.