Large-Scale Network Traffic Classification Using Graph Clustering-Enhanced E-GraphSAGE
Bibliographic record
Abstract
Network traffic classification is a key technology for intrusion detection systems, but traditional methods face bottlenecks such as high computational complexity and large memory consumption when handling large-scale graph-structured data. To address this challenge, this paper proposes the Cluster-E-GraphSAGE framework, which innovatively combines edge-aware graph neural networks with the METIS graph partitioning algorithm to achieve efficient processing of large-scale network traffic graphs through an efficient subgraph partitioning strategy and edge-aware message passing mechanism. The framework supports multi-directed graph structures, completely preserving edge multiplicity and feature attributes, and significantly reduces computational complexity and memory overhead through edge-based subgraph partitioning. Experiments on the standard NF-BoT-IoT and NF-ToN-IoT datasets show that Cluster-E-GraphSAGE performs particularly well in multi-class classification tasks, achieving F1 scores of 92.82% and 81.32% respectively, which are 11.23% and 23.6% improvements over baseline methods. Meanwhile, it reduces memory usage by 4-7 times and GPU memory by 8-11 times. The research results verify that the method maintains high classification accuracy while significantly reducing memory overhead in resource-constrained environments, demonstrating its application potential in real-time intrusion detection scenarios.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.005 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".