REAL-TIME FINANCIAL FRAUD DETECTION USING A FEATURE-LIGHT TEMPORAL DYNAMIC GRAPH NEURAL NETWORK WITH CONTRASTIVE LEARNING
Keywords:
Financial fraud detection, Anti-money laundering, Temporal graph neural network, Contrastive learning, Class imbalance, Elliptic Bitcoin datasetAbstract
Financial fraud detection is a rare-event, non-stationary graph classification problem in which relational patterns can change faster than labels become available. This paper presents FT-TDGCL, a feature-light temporal directed graph neural network with contrastive learning for near-real-time anti-money-laundering screening. Unlike approaches that depend on the 166 anonymized Elliptic attributes, the proposed pipeline uses only the public directed transaction edge list and labels. It derives 18 auditable topology features, applies incoming and outgoing graph filters at one and two hops, and fuses a node embedding with a causal gated recurrent snapshot context. During training, two independently channel-masked and noise-perturbed graph-filtered views are aligned with an NT-Xent objective in addition to class-balanced binary cross-entropy. We evaluate on the real Elliptic Bitcoin graph with 203,769 transactions, 234,355 payment flows, and 49 temporal steps. A strict chronological split uses steps 1–29 for training, 30–34 for validation and threshold selection, and 35–49 for testing; unknown labels participate only in topology construction. Across three seeds, FT-TDGCL obtains a test PR-AUC of 0.2152±0.0935 versus 0.1655±0.0333 without contrastive learning, a 30.0% relative gain. It reaches recall 0.5429±0.0444, while its F1 of 0.2344±0.0393 does not surpass every fixed-seed baseline, exposing a calibration trade-off rather than a universal improvement. Cached-feature inference over 16,670 labeled test nodes requires 6.95±0.64 ms on CPU. All metrics, predictions, hashes, and code are generated by the accompanying reproducibility package; no synthetic observations or hand-entered experimental results are used.References
[1] Davis J, Goadrich M. The Relationship Between Precision-Recall and ROC Curves. In: Proceedings of the International Conference on Machine Learning (ICML), 2006: 233-240.
[2] Saito T, Rehmsmeier M. The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets. PLoS ONE, 2015, 10(3): e0118432.
[3] Kipf T N, Welling M. Semi-Supervised Classification with Graph Convolutional Networks. In: Proceedings of the International Conference on Learning Representations (ICLR), 2017.
[4] Hamilton W L, Ying R, Leskovec J. Inductive Representation Learning on Large Graphs. In: Advances in Neural Information Processing Systems (NeurIPS), 2017: 1024-1034.
[5] Veličković P, Cucurull G, Casanova A, et al. Graph Attention Networks. In: Proceedings of the International Conference on Learning Representations (ICLR), 2018.
[6] Wu F, Souza A, Zhang T, et al. Simplifying Graph Convolutional Networks. In: Proceedings of the International Conference on Machine Learning (ICML), 2019, 97: 6861-6871.
[7] Weber M, Domeniconi G, Chen J, et al. Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics. arXiv:1908.02591, 2019.
[8] Cho K, Merriënboer B, Gulcehre C, et al. Learning Phrase Representations Using RNN Encoder–Decoder for Statistical Machine Translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014: 1724-1734.
[9] You Y, Chen T, Sui Y, et al. Graph Contrastive Learning with Augmentations. In: Advances in Neural Information Processing Systems (NeurIPS), 2020: 5812-5823.
[10] Zhu Y, Xu Y, Yu F, et al. Deep Graph Contrastive Representation Learning. arXiv:2006.04131, 2020.
[11] Hassani K, Khasahmadi A H. Contrastive Multi-View Representation Learning on Graphs. In: Proceedings of the International Conference on Machine Learning (ICML), 2020, 119: 4116-4126.
[12] Qiu J, Chen Q, Dong Y, et al. GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training. In: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2020: 1150-1160.
[13] Chen T, Kornblith S, Norouzi M, et al. A Simple Framework for Contrastive Learning of Visual Representations. In: Proceedings of the International Conference on Machine Learning (ICML), 2020, 119: 1597-1607.
[14] Khosla P, Teterwak P, Wang C, et al. Supervised Contrastive Learning. In: Advances in Neural Information Processing Systems (NeurIPS), 2020: 18661-18673.
[15] van den Oord A, Li Y, Vinyals O. Representation Learning with Contrastive Predictive Coding. arXiv:1807.03748, 2018.
[16] Pareja A, Domeniconi G, Chen J, et al. EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020, 34(4): 5363-5370.
[17] Sankar A, Wu Y, Gou L, et al. DySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention Networks. In: Proceedings of the ACM International Conference on Web Search and Data Mining (WSDM), 2020: 519-527.
[18] Xu D, Ruan C, Korpeoglu E, et al. Inductive Representation Learning on Temporal Graphs. In: Proceedings of the International Conference on Learning Representations (ICLR), 2020.
[19] Rossi E, Chamberlain B, Frasca F, et al. Temporal Graph Networks for Deep Learning on Dynamic Graphs. arXiv:2006.10637, 2020.
[20] Trivedi R, Farajtabar M, Biswal P, et al. DyRep: Learning Representations over Dynamic Graphs. In: Proceedings of the International Conference on Learning Representations (ICLR), 2019.
[21] Kumar S, Zhang X, Leskovec J. Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks. In: Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), 2019: 1269-1278.
[22] Dou Y, Liu Z, Sun L, et al. Enhancing Graph Neural Network-Based Fraud Detectors against Camouflaged Fraudsters. In: Proceedings of the ACM International Conference on Information and Knowledge Management (CIKM), 2020: 325-334.
[23] Liu Y, Ao X, Qin Z, et al. Pick and Choose: A GNN-Based Imbalanced Learning Approach for Fraud Detection. In: Proceedings of The Web Conference, 2021: 3168-3177.
[24] Ding K, Li J, Bhanushali R, et al. Deep Anomaly Detection on Attributed Networks. In: Proceedings of the SIAM International Conference on Data Mining (SDM), 2019: 594-602.
[25] Akoglu L, Tong H, Koutra D. Graph Based Anomaly Detection and Description: A Survey. Data Mining and Knowledge Discovery, 2015, 29: 626-688.
[26] Lin T-Y, Goyal P, Girshick R, et al. Focal Loss for Dense Object Detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2017: 2980-2988.
[27] Page L, Brin S, Motwani R, et al. The PageRank Citation Ranking: Bringing Order to the Web. Stanford InfoLab, Technical Report 1999-66, 1999.
[28] Breiman L. Random Forests. Machine Learning, 2001, 45: 5-32.
[29] Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 2011, 12: 2825-2830.
[30] Loshchilov I, Hutter F. Decoupled Weight Decay Regularization. In: Proceedings of the International Conference on Learning Representations (ICLR), 2019.