Heterophilic Graph Invariant Learning for Out-of-Distribution of Fraud Detection

Lingfei Ren, Ruimin Hu, Zheng Wang, Yilin Xiao, Dengshi Li, Junhang Wu, Jinzhang Hu, Yilong Zang, Zijun Huang

Abstract: Graph-based fraud detection (GFD) has garnered increasing attention due to its effectiveness in identifying fraudsters within multimedia data such as online transactions, product reviews, or telephone voices. However, the prevalent in-distribution (ID) assumption significantly impedes the generalization of GFD approaches to out-of-distribution (OOD) scenarios, which is a pervasive challenge considering the dynamic nature of fraudulent activities. In this paper, we introduce the Heterophilic Graph Invariant Learning Framework (HGIF), a novel approach to bolster the OOD generalization of GFD. HGIF addresses two pivotal challenges: creating diverse virtual training environments and adapting to varying target distributions. Leveraging edge-aware augmentation, HGIF efficiently generates multiple virtual training environments characterized by generalized heterophily distributions, thereby facilitating robust generalization against fraud graphs with diverse heterophily degrees. Moreover, HGIF employs a shared dual-channel encoder with heterophilic graph contrastive learning, enabling the model to acquire stable high-pass and low-pass node representations during training. During the Test-time Training phase, the shared dual-channel encoder is flexibly fine-tuned to adapt to the test distribution through graph contrastive learning. Extensive experiments showcase HGIF's superior performance over existing methods in OOD generalization, setting a new benchmark for GFD in OOD scenarios.

Primary Subject Area: [Systems] Data Systems Management and Indexing

Relevance To Conference: Our research is closely related to multimedia analytics. Our data sources mainly include multimedia data such as online transactions, product reviews, telephone voice, and purchase records. Our goal is to identify and mine fraudulent accounts or entities in multimedia application platforms. Our research will help improve the anti-fraud capabilities of multimedia platforms.

Submission Number: 3350