When Graph Structure Becomes a Liability: A Critical Re-Evaluation of Graph Neural Networks for Bitcoin Fraud Detection under Temporal Distribution Shift

• URL: http://arxiv.org/abs/2604.19514v1
• Date: Tue, 21 Apr 2026 14:32:20 GMT
• Title: When Graph Structure Becomes a Liability: A Critical Re-Evaluation of Graph Neural Networks for Bitcoin Fraud Detection under Temporal Distribution Shift
• Abstract summary: Random Forest on raw features achieves F1 = 0.821 and outperforms all evaluated GNNs, while GraphSAGE reaches F1 = 0.689 +/- 0.017.<n>We release code, checkpoints, and a strict-inductive protocol to enable reproducible, leakage-free evaluation.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The consensus that GCN, GraphSAGE, GAT, and EvolveGCN outperform feature-only baselines on the Elliptic Bitcoin Dataset is widely cited but has not been rigorously stress-tested under a leakage-free evaluation protocol. We perform a seed-matched inductive-versus-transductive comparison and find that this consensus does not hold. Under a strictly inductive protocol, Random Forest on raw features achieves F1 = 0.821 and outperforms all evaluated GNNs, while GraphSAGE reaches F1 = 0.689 +/- 0.017. A paired controlled experiment reveals a 39.5-point F1 gap attributable to training-time exposure to test-period adjacency. Additionally, edge-shuffle ablations show that randomly wired graphs outperform the real transaction graph, indicating that the dataset's topology can be misleading under temporal distribution shift. Hybrid models combining GNN embeddings with raw features provide only marginal gains and remain substantially below feature-only baselines. We release code, checkpoints, and a strict-inductive protocol to enable reproducible, leakage-free evaluation.

Related papers

• Semi-Supervised Learning on Graphs using Graph Neural Networks [7.3886152750469]
  Graph neural networks (GNNs) work remarkably well in semi-supervised node regression.<n>We study an aggregate-and-readout model that encompasses several common message passing architectures.<n>We prove a sharp non-asymptotic risk bound that separates errors approximation, convergence, and optimization.
  arXiv  Detail & Related papers  (2026-02-19T06:25:13Z)
• How does Graph Structure Modulate Membership-Inference Risk for Graph Neural Networks? [0.34546020643989767]
  Graph neural networks (GNNs) have become the standard tool for encoding data and their complex relationships into continuous representations.<n>Their use in sensitive applications has raised concerns about the potential leakage of training data.<n>Research on privacy leakage in GNNs has largely been shaped by findings from non-graph domains.
  arXiv  Detail & Related papers  (2026-01-23T19:08:36Z)
• Interpretable and Adaptive Node Classification on Heterophilic Graphs via Combinatorial Scoring and Hybrid Learning [1.2691047660244335]
  Graph neural networks (GNNs) achieve strong performance on homophilic graphs but often struggle underphily, where adjacent nodes frequently belong to different classes.<n>We propose an interpretable and adaptive framework for semi-supervised node classification based on explicit inference rather than deep message passing.<n> Experiments on heterophilic and transitional benchmarks demonstrate competitive performance with modern GNNs while offering advantages in interpretability, tuna, and computational efficiency.
  arXiv  Detail & Related papers  (2025-12-22T20:50:44Z)
• Online GNN Evaluation Under Test-time Graph Distribution Shifts [92.4376834462224]
  A new research problem, online GNN evaluation, aims to provide valuable insights into the well-trained GNNs's ability to generalize to real-world unlabeled graphs. We develop an effective learning behavior discrepancy score, dubbed LeBeD, to estimate the test-time generalization errors of well-trained GNN models.
  arXiv  Detail & Related papers  (2024-03-15T01:28:08Z)
• Graph Out-of-Distribution Generalization via Causal Intervention [69.70137479660113]
  We introduce a conceptually simple yet principled approach for training robust graph neural networks (GNNs) under node-level distribution shifts. Our method resorts to a new learning objective derived from causal inference that coordinates an environment estimator and a mixture-of-expert GNN predictor. Our model can effectively enhance generalization with various types of distribution shifts and yield up to 27.4% accuracy improvement over state-of-the-arts on graph OOD generalization benchmarks.
  arXiv  Detail & Related papers  (2024-02-18T07:49:22Z)
• FRGNN: Mitigating the Impact of Distribution Shift on Graph Neural Networks via Test-Time Feature Reconstruction [13.21683198528012]
  A distribution shift can adversely affect the test performance of Graph Neural Networks (GNNs) We propose FR-GNN, a general framework for GNNs to conduct feature reconstruction. Notably, the reconstructed node features can be directly utilized for testing the well-trained model.
  arXiv  Detail & Related papers  (2023-08-18T02:34:37Z)
• Uncertainty Quantification over Graph with Conformalized Graph Neural Networks [52.20904874696597]
  Graph Neural Networks (GNNs) are powerful machine learning prediction models on graph-structured data. GNNs lack rigorous uncertainty estimates, limiting their reliable deployment in settings where the cost of errors is significant. We propose conformalized GNN (CF-GNN), extending conformal prediction (CP) to graph-based models for guaranteed uncertainty estimates.
  arXiv  Detail & Related papers  (2023-05-23T21:38:23Z)
• Understanding Non-linearity in Graph Neural Networks from the Bayesian-Inference Perspective [33.01636846541052]
  Graph neural networks (GNNs) have shown superiority in many prediction tasks over graphs. We investigate the functions of non-linearity in GNNs for node classification tasks.
  arXiv  Detail & Related papers  (2022-07-22T19:36:12Z)
• ResNorm: Tackling Long-tailed Degree Distribution Issue in Graph Neural Networks via Normalization [80.90206641975375]
  This paper focuses on improving the performance of GNNs via normalization. By studying the long-tailed distribution of node degrees in the graph, we propose a novel normalization method for GNNs. The $scale$ operation of ResNorm reshapes the node-wise standard deviation (NStd) distribution so as to improve the accuracy of tail nodes.
  arXiv  Detail & Related papers  (2022-06-16T13:49:09Z)
• Mixed Graph Contrastive Network for Semi-Supervised Node Classification [63.924129159538076]
  We propose a novel graph contrastive learning method, termed Mixed Graph Contrastive Network (MGCN)<n>In our method, we improve the discriminative capability of the latent embeddings by an unperturbed augmentation strategy and a correlation reduction mechanism.<n>By combining the two settings, we extract rich supervision information from both the abundant nodes and the rare yet valuable labeled nodes for discriminative representation learning.
  arXiv  Detail & Related papers  (2022-06-06T14:26:34Z)
• Stable Prediction on Graphs with Agnostic Distribution Shift [105.12836224149633]
  Graph neural networks (GNNs) have been shown to be effective on various graph tasks with randomly separated training and testing data. In real applications, however, the distribution of training graph might be different from that of the test one. We propose a novel stable prediction framework for GNNs, which permits both locally and globally stable learning and prediction on graphs.
  arXiv  Detail & Related papers  (2021-10-08T02:45:47Z)

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.