Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910160269606912 |
|---|---|
| author | Anyfantis, Georgios Barlet-Ros, Pere |
| author_facet | Anyfantis, Georgios Barlet-Ros, Pere |
| contents | In this paper, we propose a proof-of-concept Graph Neural Network model that can successfully predict network flow-level traffic (NetFlow) by accurately modelling the graph structure and the connection features. We use sliding-windows to split the network traffic in equal-sized heterogeneous bidirectional graphs containing IP, Port, and Connection nodes. We then use the GNN to model the evolution of the graph structure and the connection features. Our approach shows superior results when identifying the Port and IP to which connections attach, while feature reconstruction remains competitive with strong forecasting baselines. Overall, our work showcases the use of GNNs for per-flow NetFlow prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20483 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder Anyfantis, Georgios Barlet-Ros, Pere Networking and Internet Architecture Machine Learning In this paper, we propose a proof-of-concept Graph Neural Network model that can successfully predict network flow-level traffic (NetFlow) by accurately modelling the graph structure and the connection features. We use sliding-windows to split the network traffic in equal-sized heterogeneous bidirectional graphs containing IP, Port, and Connection nodes. We then use the GNN to model the evolution of the graph structure and the connection features. Our approach shows superior results when identifying the Port and IP to which connections attach, while feature reconstruction remains competitive with strong forecasting baselines. Overall, our work showcases the use of GNNs for per-flow NetFlow prediction. |
| title | Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder |
| topic | Networking and Internet Architecture Machine Learning |
| url | https://arxiv.org/abs/2604.20483 |