A Depth-Aware Comparative Study of Euclidean and Hyperbolic Graph Neural Networks on Bitcoin Transaction Systems

• URL: http://arxiv.org/abs/2603.16080v1
• Date: Tue, 17 Mar 2026 02:58:29 GMT
• Title: A Depth-Aware Comparative Study of Euclidean and Hyperbolic Graph Neural Networks on Bitcoin Transaction Systems
• Abstract summary: We conduct a comparison of Euclidean and tangent-space hyperbolic GNNs for node classification on a large Bitcoin transaction graph.<n>Our findings provide practical insights into the role of embedding geometry and neighborhood depth when modeling large-scale transaction networks.
• Score: 2.5489046505746704
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Bitcoin transaction networks are large scale socio- technical systems in which activities are represented through multi-hop interaction patterns. Graph Neural Networks(GNNs) have become a widely adopted tool for analyzing such systems, supporting tasks such as entity detection and transaction classification. Large-scale datasets like Elliptic have allowed for a rise in the analysis of these systems and in tasks such as fraud detection. In these settings, the amount of transactional context available to each node is determined by the neighborhood aggregation and sampling strategies, yet the interaction between these receptive fields and embedding geometry has received limited attention. In this work, we conduct a controlled comparison of Euclidean and tangent-space hyperbolic GNNs for node classification on a large Bitcoin transaction graph. By explicitly varying the neighborhood while keeping the model architecture and dimensionality fixed, we analyze the differences in two embedding spaces. We further examine optimization behavior and observe that joint selection of learning rate and curvature plays a critical role in stabilizing high-dimensional hyperbolic embeddings. Overall, our findings provide practical insights into the role of embedding geometry and neighborhood depth when modeling large-scale transaction networks, informing the deployment of hyperbolic GNNs for computational social systems.

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)
• GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs [59.61242815508687]
  Graph neural networks (GNNs) on text--attributed graphs (TAGs) encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear neighborhood aggregation.<n>This work introduces a local PCA-based metric that measures the degree of semantic drift and provides the first quantitative framework to analyze how different aggregation mechanisms affect manifold structure.
  arXiv  Detail & Related papers  (2025-11-12T06:48:43Z)
• Representation Learning on Large Non-Bipartite Transaction Networks using GraphSAGE [0.9415859226090767]
  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.
  arXiv  Detail & Related papers  (2025-09-12T14:09:16Z)
• ScaleGNN: Towards Scalable Graph Neural Networks via Adaptive High-order Neighboring Feature Fusion [73.85920403511706]
  We propose ScaleGNN, a novel framework that adaptively fuses multi-hop node features for scalable and effective graph learning.<n>We show that ScaleGNN consistently outperforms state-of-the-art GNNs in both predictive accuracy and computational efficiency.
  arXiv  Detail & Related papers  (2025-04-22T14:05:11Z)
• Hyperbolic Benchmarking Unveils Network Topology-Feature Relationship in GNN Performance [0.5416466085090772]
  We introduce a comprehensive benchmarking framework for graph machine learning. We generate synthetic networks with realistic topological properties and node feature vectors. Results highlight the dependency of model performance on the interplay between network structure and node features.
  arXiv  Detail & Related papers  (2024-06-04T20:40:06Z)
• Sifting out communities in large sparse networks [2.666294200266662]
  We introduce an intuitive objective function for quantifying the quality of clustering results in large sparse networks. We utilize a two-step method for identifying communities which is especially well-suited for this domain. We identify complex genetic interactions in large-scale networks comprised of tens of thousands of nodes.
  arXiv  Detail & Related papers  (2024-05-01T18:57:41Z)
• 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)
• Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis [94.64007376939735]
  We theoretically characterize the impact of connectivity patterns on the convergence of deep neural networks (DNNs) under gradient descent training. We show that by a simple filtration on "unpromising" connectivity patterns, we can trim down the number of models to evaluate.
  arXiv  Detail & Related papers  (2022-05-11T17:43:54Z)
• BScNets: Block Simplicial Complex Neural Networks [79.81654213581977]
  Simplicial neural networks (SNN) have recently emerged as the newest direction in graph learning. We present Block Simplicial Complex Neural Networks (BScNets) model for link prediction. BScNets outperforms state-of-the-art models by a significant margin while maintaining low costs.
  arXiv  Detail & Related papers  (2021-12-13T17:35:54Z)
• Tree Decomposed Graph Neural Network [11.524511007436791]
  We propose a tree decomposition method to disentangle neighborhoods in different layers to alleviate feature smoothing. We also characterize the multi-hop dependency via graph diffusion within our tree decomposition formulation to construct Tree Decomposed Graph Neural Network (TDGNN) Comprehensive experiments demonstrate the superior performance of TDGNN on both homophily and heterophily networks.
  arXiv  Detail & Related papers  (2021-08-25T02:47:16Z)
• Towards Deeper Graph Neural Networks [63.46470695525957]
  Graph convolutions perform neighborhood aggregation and represent one of the most important graph operations. Several recent studies attribute this performance deterioration to the over-smoothing issue. We propose Deep Adaptive Graph Neural Network (DAGNN) to adaptively incorporate information from large receptive fields.
  arXiv  Detail & Related papers  (2020-07-18T01:11:14Z)
• Binarized Graph Neural Network [65.20589262811677]
  We develop a binarized graph neural network to learn the binary representations of the nodes with binary network parameters. Our proposed method can be seamlessly integrated into the existing GNN-based embedding approaches. Experiments indicate that the proposed binarized graph neural network, namely BGN, is orders of magnitude more efficient in terms of both time and space.
  arXiv  Detail & Related papers  (2020-04-19T09:43:14Z)

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.