The Shape of Money Laundering: Subgraph Representation Learning on the Blockchain with the Elliptic2 Dataset

arXiv:2404.19109v1 Announce Type: new
Abstract: Subgraph representation learning is a technique for analyzing local structures (or shapes) within complex networks. Enabled by recent developments in scalable Graph Neural Networks (GNNs), this approach encodes relational information at a subgroup level (multiple connected nodes) rather than at a node level of abstraction. We posit that certain domain applications, such as anti-money laundering (AML), are inherently subgraph problems and mainstream graph techniques have been operating at a suboptimal level of abstraction. This is …

abstract arxiv blockchain cs.lg dataset gnns graph graph neural networks information money multiple networks neural networks nodes q-fin.gn relational representation representation learning scalable type