HiLoMix: Robust High- and Low-Frequency Graph Learning Framework for Mixing Address Association

TL;DR

HiLoMix is a novel graph-based framework that enhances mixing address association by integrating heterogeneous graph construction, frequency-aware contrastive learning, weak supervision, and model stacking to improve robustness against label noise and scarcity.

Contribution

The paper introduces HiLoMix, a comprehensive graph learning framework combining heterogeneous graph construction, frequency-aware contrastive learning, and stacking to improve mixing address association.

Findings

Outperforms existing methods in accuracy.

Robust against label noise and scarcity.

Effective in real-world transaction networks.

Abstract

As mixing services are increasingly being exploited by malicious actors for illicit transactions, mixing address association has emerged as a critical research task. A range of approaches have been explored, with graph-based models standing out for their ability to capture structural patterns in transaction networks. However, these approaches face two main challenges: label noise and label scarcity, leading to suboptimal performance and limited generalization. To address these, we propose HiLoMix, a graph-based learning framework specifically designed for mixing address association. First, we construct the Heterogeneous Attributed Mixing Interaction Graph (HAMIG) to enrich the topological structure. Second, we introduce frequency-aware graph contrastive learning that captures complementary structural signals from high- and low-frequency graph views. Third, we employ weak supervised learning that assigns confidence-based weighting to noisy labels. Then, we jointly train high-pass and low-pass GNNs using both unsupervised contrastive signals and confidence-based supervision to learn robust node representations. Finally, we adopt a stacking framework to fuse predictions from multiple heterogeneous models, further improving generalization and robustness. Experimental results demonstrate that HiLoMix outperforms existing methods in mixing address association.