Federated Graph Fraud Detection with Spectral Adaptation and Confidence-Aware Aggregation

Graph-based Fraud Detection (GFD), which aims to identify fraud patterns within interaction networks, has attracted significant interest in trustworthy machine learning. However, real-world privacy regulations distribute graph data across decentralized clients, where fraudsters exhibit severe spectral heterogeneity both within and across these silos. Consequently, existing centralized fraud detectors relying on static filter banks fail to capture intricate patterns. More critically, fraudsters deliberately isolate themselves to evade detection, rendering any graph filter that operates via message-passing schemes completely ineffective. To address these challenges, we propose a federated learning framework featuring two major techniques: (1) $\text{FedSACA}$, which employs dynamic spectral channel attention to handle intra-client heterogeneity, and performs per-frequency confidence-aware aggregation on filter coefficients to tackle inter-client heterogeneity. (2) $\text{FedSACA+}$, which extends FedSACA with a feature-induced structure augmentation subject to the frequency confidence evaluation, thereby preventing the introduction of potential noise. Extensive experiments on multiple datasets demonstrate the superior performance of our proposed techniques.