Knowledge-Integrated Representation Learning for Crypto Anomaly Detection under Extreme Label Scarcity; Relational Domain-Logic Integration with Retrieval-Grounded Context and Path-Level Explanations

TL;DR

The paper tackles anomaly detection in decentralized crypto networks under extreme label scarcity and FATF Travel Rule requirements for interpretable, auditable reasoning. It introduces Relational Domain-Logic Integration (RDLI), a neuro-symbolic framework that fuses expert heuristics (via an Expert Knowledge Graph), retrieval-grounded market/contextual information, and path-level explanations to reconstruct multi-hop, logic-driven money flows. RDLI demonstrates substantial performance gains (notably a $28.9\%$ F1 improvement under $0.01\%$ labeled data) over strong GNN baselines, and a micro-expert study confirms improved trust and perceived usefulness of path-centric explanations. The approach generalizes across financial domains (crypto and card transactions) and emphasizes explainability aligned with regulatory needs, offering a practical, auditable solution for robust, regulation-compliant financial monitoring.

Abstract

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.

Figures (2)

• Figure 1: Overview of the RDLI framework
• Figure 2: SHAP-based top-5 feature importance for the LightGBM (Full) model.