DPF-GFD uses complementary frequency filtering on the original graph and a similarity graph to produce more discriminative node embeddings for fraud detection under high heterophily and class imbalance.
Specformer: Spectral graph neural networks meet transformers
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
-
Graph-Based Fraud Detection with Dual-Path Graph Filtering
DPF-GFD uses complementary frequency filtering on the original graph and a similarity graph to produce more discriminative node embeddings for fraud detection under high heterophily and class imbalance.