Enhanced Pre-Trained Graph Neural Networks with Applications in Financial Fraud Detection
Bibliographic record
Abstract
Graph Neural Networks (GNNs) have demonstrated strong potentials in identifying complex patterns and detecting anomalies in large data. While pre-training has proven highly effective in domains such as natural language processing and computer vision, its application in graph-based tasks remains under-explored due to the risk of negative transfer. In the context of GNNs, pre-training helps capture general graph-based relational patterns, enhancing performance in downstream tasks such as fraud detection by fine-tuning on a domain-specific dataset. This research explores how pre-training can enhance the performance of GNNs first by proposing a modular framework, which provides flexibility to experiment with different configurations. The proposed framework aims to systematically integrate configurable modules for dataset selection, pre-training task design, and model configuration. Second, to demonstrate the effectiveness of pre-training in graph-based data analysis, we pre-train a model on a large available dataset, then employ it for fraud detection in finance domain where availability of data could be limited. We perform an experiment leveraging the large DGraphFin dataset for pre-training, and the Elliptic dataset for fine-tuning. The pre-trained GNN achieves notable performance improvements, with an F1 score of 88.7% and a recall of 0.831, surpassing prior benchmarks. The findings affirm the transformative potential of pre-training in graph-based tasks, particularly in financial fraud detection. Pre-training enhanced both the accuracy and robustness of fraud detection models, making it a worthwhile approach to explore for addressing the challenges of real-world financial fraud.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".