Knowledge-Integrated Representation Learning for Crypto Anomaly Detection under Extreme Label Scarcity; Relational Domain-Logic Integration with Retrieval-Grounded Context and Path-Level Explanations
This work addresses the challenge of crypto anomaly detection for regulatory compliance under extreme label scarcity, representing a domain-specific advancement with incremental methodological integration.
The paper tackles the problem of detecting anomalous trajectories in decentralized crypto networks under extreme label scarcity (0.01%) by proposing the Relational Domain Logic Integration (RDLI) framework, which embeds expert-derived heuristics as logic-aware latent signals and incorporates retrieval-grounded context to mitigate false positives. The result is a 28.9% improvement in F1 score over state-of-the-art GNN baselines, with path-level explanations enhancing trustworthiness and clarity in expert user studies.
Detecting anomalous trajectories in decentralized crypto networks is fundamentally challenged by extreme label scarcity and the adaptive evasion strategies of illicit actors. While Graph Neural Networks (GNNs) effectively capture local structural patterns, they struggle to internalize multi hop, logic driven motifs such as fund dispersal and layering that characterize sophisticated money laundering, limiting their forensic accountability under regulations like the FATF Travel Rule. To address this limitation, we propose Relational Domain Logic Integration (RDLI), a framework that embeds expert derived heuristics as differentiable, logic aware latent signals within representation learning. Unlike static rule based approaches, RDLI enables the detection of complex transactional flows that evade standard message passing. To further account for market volatility, we incorporate a Retrieval Grounded Context (RGC) module that conditions anomaly scoring on regulatory and macroeconomic context, mitigating false positives caused by benign regime shifts. Under extreme label scarcity (0.01%), RDLI outperforms state of the art GNN baselines by 28.9% in F1 score. A micro expert user study further confirms that RDLI path level explanations significantly improve trustworthiness, perceived usefulness, and clarity compared to existing methods, highlighting the importance of integrating domain logic with contextual grounding for both accuracy and explainability.