Representation Learning on Large Non-Bipartite Transaction Networks using GraphSAGE

• URL: http://arxiv.org/abs/2509.12255v1
• Date: Fri, 12 Sep 2025 14:09:16 GMT
• Title: Representation Learning on Large Non-Bipartite Transaction Networks using GraphSAGE
• Authors: Mihir Tare, Clemens Rattasits, Yiming Wu, Euan Wielewski,
• Abstract summary: This paper demonstrates the practical application of GraphSAGE, an inductive Graph Neural Network framework, to non-bipartite heterogeneous transaction networks within a banking context.<n>We construct a transaction network using anonymised customer and merchant transactions and train a GraphSAGE model to generate node embeddings.<n>Our work highlights the adaptability of this framework to banking-scale networks, emphasising its inductive capability, scalability, and interpretability.
• Score: 0.9415859226090767
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Financial institutions increasingly require scalable tools to analyse complex transactional networks, yet traditional graph embedding methods struggle with dynamic, real-world banking data. This paper demonstrates the practical application of GraphSAGE, an inductive Graph Neural Network framework, to non-bipartite heterogeneous transaction networks within a banking context. Unlike transductive approaches, GraphSAGE scales well to large networks and can generalise to unseen nodes which is critical for institutions working with temporally evolving transactional data. We construct a transaction network using anonymised customer and merchant transactions and train a GraphSAGE model to generate node embeddings. Our exploratory work on the embeddings reveals interpretable clusters aligned with geographic and demographic attributes. Additionally, we illustrate their utility in downstream classification tasks by applying them to a money mule detection model where using these embeddings improves the prioritisation of high-risk accounts. Beyond fraud detection, our work highlights the adaptability of this framework to banking-scale networks, emphasising its inductive capability, scalability, and interpretability. This study provides a blueprint for financial organisations to harness graph machine learning for actionable insights in transactional ecosystems.

Related papers

• Interpreting Manifolds and Graph Neural Embeddings from Internet of Things Traffic Flows [1.8510825807956957]
  This work introduces an interpretable pipeline that generates directly visualizable low-dimensional representations by mapping high-dimensional embeddings onto a latent manifold.<n>The framework achieves a classification F1-score of 0.830 for intrusion detection while also highlighting phenomena such as concept drift.
  arXiv  Detail & Related papers  (2026-02-05T16:08:24Z)
• Detecting Credit Card Fraud via Heterogeneous Graph Neural Networks with Graph Attention [2.7002727600755883]
  This study proposes a credit card fraud detection method based on Heterogeneous Graph Neural Network (HGNN)<n>By leveraging graph neural networks, the model captures higher-order transaction relationships.<n>The model achieves notable improvements in both accuracy and OC-ROC.
  arXiv  Detail & Related papers  (2025-04-11T00:53:53Z)
• Towards Graph Foundation Models: Learning Generalities Across Graphs via Task-Trees [50.78679002846741]
  We propose a novel approach to cross-task generalization in graphs via task-trees.<n>We show that pretraining a graph neural network (GNN) on diverse task-trees with a reconstruction objective induces transferable knowledge.<n>This enables efficient adaptation to downstream tasks with minimal fine-tuning.
  arXiv  Detail & Related papers  (2024-12-21T02:07:43Z)
• T-GAE: Transferable Graph Autoencoder for Network Alignment [79.89704126746204]
  T-GAE is a graph autoencoder framework that leverages transferability and stability of GNNs to achieve efficient network alignment without retraining. Our experiments demonstrate that T-GAE outperforms the state-of-the-art optimization method and the best GNN approach by up to 38.7% and 50.8%, respectively.
  arXiv  Detail & Related papers  (2023-10-05T02:58:29Z)
• Scalable and Weakly Supervised Bank Transaction Classification [0.0]
  This paper aims to categorize bank transactions using weak supervision, natural language processing, and deep neural network training. We present an effective and scalable end-to-end data pipeline, including data preprocessing, transaction text embedding, anchoring, label generation, discriminative neural network training.
  arXiv  Detail & Related papers  (2023-05-28T23:12:12Z)
• Temporal Graph Network Embedding with Causal Anonymous Walks Representations [54.05212871508062]
  We propose a novel approach for dynamic network representation learning based on Temporal Graph Network. For evaluation, we provide a benchmark pipeline for the evaluation of temporal network embeddings. We show the applicability and superior performance of our model in the real-world downstream graph machine learning task provided by one of the top European banks.
  arXiv  Detail & Related papers  (2021-08-19T15:39:52Z)
• Relational Graph Neural Networks for Fraud Detection in a Super-App environment [53.561797148529664]
  We propose a framework of relational graph convolutional networks methods for fraudulent behaviour prevention in the financial services of a Super-App. We use an interpretability algorithm for graph neural networks to determine the most important relations to the classification task of the users. Our results show that there is an added value when considering models that take advantage of the alternative data of the Super-App and the interactions found in their high connectivity.
  arXiv  Detail & Related papers  (2021-07-29T00:02:06Z)
• Graph-Based Neural Network Models with Multiple Self-Supervised Auxiliary Tasks [79.28094304325116]
  Graph Convolutional Networks are among the most promising approaches for capturing relationships among structured data points. We propose three novel self-supervised auxiliary tasks to train graph-based neural network models in a multi-task fashion.
  arXiv  Detail & Related papers  (2020-11-14T11:09:51Z)
• Discriminability of Single-Layer Graph Neural Networks [172.5042368548269]
  Graph neural networks (GNNs) have exhibited promising performance on a wide range of problems. We focus on the property of discriminability and establish conditions under which the inclusion of pointwise nonlinearities to a stable graph filter bank leads to an increased discriminative capacity for high-eigenvalue content.
  arXiv  Detail & Related papers  (2020-10-17T18:52:34Z)
• EWS-GCN: Edge Weight-Shared Graph Convolutional Network for Transactional Banking Data [2.1169216065483996]
  We show that information about connections between clients based on money transfers between them allows us to significantly improve the quality of credit scoring. We develop a new graph neural network model EWS-GCN that combines ideas of graph convolutional and recurrent neural networks via attention mechanism.
  arXiv  Detail & Related papers  (2020-09-30T12:09:28Z)
• GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training [62.73470368851127]
  Graph representation learning has emerged as a powerful technique for addressing real-world problems. We design Graph Contrastive Coding -- a self-supervised graph neural network pre-training framework. We conduct experiments on three graph learning tasks and ten graph datasets.
  arXiv  Detail & Related papers  (2020-06-17T16:18:35Z)
• Linking Bank Clients using Graph Neural Networks Powered by Rich Transactional Data [2.1169216065483996]
  We propose a new graph neural network model, which uses not only the topological structure of the network but rich time-series data available for the graph nodes and edges. The proposed model outperforms the existing approaches, with a significant gap in ROC AUC score on link prediction problem and also allows to improve the quality of credit scoring.
  arXiv  Detail & Related papers  (2020-01-23T10:02:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.