Homophilic and Heterophilic-Aware Sparse Graph Transformer for Financial Fraud Detection

Fraud detection is essential across various domains, including finance and societal contexts. However, the domain of financial fraud detection is plagued by challenges such as class-imbalance, camouflage, and structural fraud. Predominant fraud detection models focus on the former issues, neglecting the nuanced intricacies of structural fraud within financial relations. For instance, in credit card cash-out fraud, fraudulent merchants attempt to blend their illicit transactions by engaging with multiple genuine users, which introduces camouflage. More critically, first-order neighbors of these fraudulent entities are often heterophilic, while their second-order neighbors typically exhibit homophily due to the reliance on intermediary accounts for illegal fund transfers, eventually directing these funds to controlled destination accounts or facilitating money laundering. The role of homophilic and heterophilic relations in multi-hop neighborhoods is paramount for the effective detection of financial fraud. Traditional Graph Neural Networks (GNNs) operate on the homophily assumption, the tendency of nodes to connect with similar others, representing nodes via neighborhood aggregation. They, however, fall short in distinguishing heterophilic interactions, leading to noise incorporation and missing valuable multi-hop neighborhood insights. To address this gap, we propose a novel algorithm named HHSGT (Homophilic and Heterophilic-Aware Sparse Graph Transformer) capable of discerning and emphasizing homophilic interactions while attenuating heterophilic noise within multi-hop neighborhoods. Our approach integrates global attribute information, computes relation scores, allows dynamic score thresholding, and employs a Sparse Graph Transformer to obtain node representation. Extensive experiments on real-world financial fraud, review, and simulated credit card cash-out dataset showcase HHSGT’s superiority over baseline methods.