A Multi-Scale Graph Learning Framework with Temporal Consistency Constraints for Financial Fraud Detection in Transaction Networks under Non-Stationary Conditions

• URL: http://arxiv.org/abs/2603.14592v1
• Date: Sun, 15 Mar 2026 20:30:02 GMT
• Title: A Multi-Scale Graph Learning Framework with Temporal Consistency Constraints for Financial Fraud Detection in Transaction Networks under Non-Stationary Conditions
• Abstract summary: STC-MixHop is a graph-based framework combining spatial multi-resolution propagation with lightweight temporal consistency modeling.<n>We evaluate the framework primarily on the PaySim dataset under strict chronological splits.<n>Results show that STC-MixHop is competitive among graph methods and achieves strong screening-oriented recall under highly imbalanced conditions.
• Score: 6.8063643637119275
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Financial fraud detection in transaction networks involves modeling sparse anomalies, dynamic patterns, and severe class imbalance in the presence of temporal drift in the data. In real-world transaction systems, a suspicious transaction is rarely isolated: rather, legitimate and suspicious transactions are often connected through accounts, intermediaries or through temporal transaction sequences. Attribute-based or randomly partitioned learning pipelines are therefore insufficient to detect relationally structured fraud. STC-MixHop, a graph-based framework combining spatial multi-resolution propagation with lightweight temporal consistency modeling for anomaly and fraud detection in dynamic transaction networks. It integrates three components: a MixHop-inspired multi-scale neighborhood diffusion encoder a multi-scale neighborhood diffusion MixHop-based encoder for learning structural patterns; a spatial-temporal attention module coupling current and preceding graph snapshots to stabilize representations; and a temporally informed self-supervised pretraining strategy exploiting unlabeled transaction interactions to improve representation quality. We evaluate the framework primarily on the PaySim dataset under strict chronological splits, supplementing the analysis with Porto Seguro and FEMA data to probe cross-domain component behavior. Results show that STC-MixHop is competitive among graph methods and achieves strong screening-oriented recall under highly imbalanced conditions. The experiments also reveal an important boundary condition: when node attributes are highly informative, tabular baselines remain difficult to outperform. Graph structure contributes most clearly where hidden relational dependencies are operationally important. These findings support a stability-focused view of graph learning for financial fraud detection.

Related papers

• Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection [4.923071905608023]
  We propose ADC-GNN, a unified framework that combines diffusion-guided feature augmentation, contrastive representation learning, and multi-hop spectral attention for few-shot fraud detection.<n>We evaluate ADC-GNN primarily on three public benchmarks and report a proprietary real-world telecom transaction dataset with approximately 60,000 records as a private case study.
  arXiv  Detail & Related papers  (2026-06-26T14:34:28Z)
• TimeLAVA: Learning-Agnostic Data Valuation for Time Series [48.76711740818533]
  TimeLAVA is a learning-agnostic framework that values temporal segments by their marginal contribution to minimize distributional discrepancy between evaluated and reference data.<n>We provide theoretical guarantees linking valuation to model-agnostic generalization and prove bounded sensitivity to contamination.
  arXiv  Detail & Related papers  (2026-06-17T06:16:16Z)
• TMR-GGNN: Credit Card Fraud Detection based on Time-Aware Multi-Relational Guided Graph Neural Network [0.0]
  This research proposes a novel framework called Timeaware Multi Guided Graph Neural Network (TM GGNN)<n>The decoder employs a contrastive learning module to distinguish between real and synthesized transaction patterns.<n>To effectively manage severe class imbalances and emphasize discriminative learning, a composite loss function combining Information Noise Contrastive Estimation (InfoNCE) based contrastive loss with Focal Loss is introduced.
  arXiv  Detail & Related papers  (2026-06-16T19:50:53Z)
• AnchorMoE: Interpretable Time Series Classification via Anchor-Routed MoE [51.994752158953084]
  AnchorMoE is an interpretable-by-construction classification framework.<n>It encodes multi-view representations of local patches and routes them to specialized experts.<n>Experiments on real-world and synthetic benchmarks demonstrate that AnchorMoE achieves highly competitive classification performance.
  arXiv  Detail & Related papers  (2026-06-02T13:30:54Z)
• Graph-Based Financial Fraud Detection with Calibrated Risk Scoring and Structural Regularization [8.94945137673605]
  This paper proposes a graph neural network representation learning and risk discrimination framework for financial transaction fraud prevention.<n>It integrates transaction records and identity information into node attributes and constructs a transaction graph based on shared attributes and interaction consistency.<n> Experiments are conducted on a publicly available financial transaction dataset.
  arXiv  Detail & Related papers  (2026-05-12T21:52:24Z)
• Hybrid LSTM-Graph Neural Framework for Robust Financial Fraud Detection and Adversarial Resilience [0.0]
  This paper proposes FraudShield AI, a hybrid framework that integrates Long Short-Term Memory (LSTM) networks with hand-crafted Graph Topological Features.<n>A Focal Loss objective is used to address class imbalance, and a dynamic thresholding mechanism is introduced to improve resilience against low-value smurfing attacks.
  arXiv  Detail & Related papers  (2026-05-02T02:10:20Z)
• Leakage Safe Graph Features for Interpretable Fraud Detection in Temporal Transaction Networks [0.0]
  This paper presents a time respecting, leakage safe (causal) graph feature extraction protocol for temporal transaction networks.<n>We construct directed transaction graphs and compute interpretable structural descriptors, including degree statistics, PageRank, HITS hub or authority scores, k-core indices, and neighborhood reachability measures.<n>Although transaction attributes remain the dominant predictive signal, graph derived features provide complementary interpretability and enable risk context analysis.
  arXiv  Detail & Related papers  (2026-02-24T05:04:06Z)
• OWLEYE: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detection [48.77471686671269]
  OWLEYE is a novel framework that learns transferable patterns of normal behavior from multiple graphs.<n>We show that OWLEYE achieves superior performance and generalizability compared to state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-01-27T02:08:18Z)
• Unsupervised Online 3D Instance Segmentation with Synthetic Sequences and Dynamic Loss [52.28880405119483]
  Unsupervised online 3D instance segmentation is a fundamental yet challenging task.<n>Existing methods, such as UNIT, have made progress in this direction but remain constrained by limited training diversity.<n>We propose a new framework that enriches the training distribution through synthetic point cloud sequence generation.
  arXiv  Detail & Related papers  (2025-09-27T08:53:27Z)
• Detecting Multilevel Manipulation from Limit Order Book via Cascaded Contrastive Representation Learning [4.11124360246468]
  Spoofing is one of the most covert and deceptive TBM strategies.<n>These patterns are usually concealed within the rich, hierarchical information of the Limit Order Book.<n>We propose a representation learning framework combining a cascaded LOB representation architecture with supervised contrastive learning.
  arXiv  Detail & Related papers  (2025-08-23T16:57:32Z)
• ACT-Tensor: Tensor Completion Framework for Financial Dataset Imputation [2.3404331106562677]
  We introduce an Adaptive, Cluster-based Temporal smoothing tensor completion framework (ACT-Tensor) for missing financial data panels.<n>ACT-Tensor consistently outperforms state-of-the-art benchmarks in terms of imputation accuracy across a range of missing data regimes.<n>Results show that ACT-Tensor not only reduces pricing errors but also significantly improves risk-adjusted returns of the constructed portfolio.
  arXiv  Detail & Related papers  (2025-08-03T17:28:57Z)
• A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detection [60.09453163562244]
  We propose a Heterophily-guided Unsupervised Graph fraud dEtection approach (HUGE) for unsupervised GFD.<n>In the estimation module, we design a novel label-free heterophily metric called HALO, which captures the critical graph properties for GFD.<n>In the alignment-based fraud detection module, we develop a joint-GNN architecture with ranking loss and asymmetric alignment loss.
  arXiv  Detail & Related papers  (2025-02-18T22:07:36Z)
• Dynamic Feature Fusion: Combining Global Graph Structures and Local Semantics for Blockchain Fraud Detection [0.7510165488300369]
  We propose a dynamic feature fusion model that combines graph-based representation learning and semantic feature extraction for fraud detection.<n>We develop a comprehensive data processing pipeline, including graph construction, temporal feature enhancement, and text preprocessing.<n> Experimental results on large-scale real-world blockchain datasets demonstrate that our method outperforms existing benchmarks across accuracy, F1 score, and recall metrics.
  arXiv  Detail & Related papers  (2025-01-03T09:04:43Z)
• Multitask Active Learning for Graph Anomaly Detection [48.690169078479116]
  We propose a novel MultItask acTIve Graph Anomaly deTEction framework, namely MITIGATE. By coupling node classification tasks, MITIGATE obtains the capability to detect out-of-distribution nodes without known anomalies. Empirical studies on four datasets demonstrate that MITIGATE significantly outperforms the state-of-the-art methods for anomaly detection.
  arXiv  Detail & Related papers  (2024-01-24T03:43:45Z)
• Transaction Fraud Detection via an Adaptive Graph Neural Network [64.9428588496749]
  We propose an Adaptive Sampling and Aggregation-based Graph Neural Network (ASA-GNN) that learns discriminative representations to improve the performance of transaction fraud detection. A neighbor sampling strategy is performed to filter noisy nodes and supplement information for fraudulent nodes. Experiments on three real financial datasets demonstrate that the proposed method ASA-GNN outperforms state-of-the-art ones.
  arXiv  Detail & Related papers  (2023-07-11T07:48:39Z)

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.