Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder

Georgios Anyfantis, Pere Barlet-Ros
4/22/2026
cs.NIcs.LG

No official code found. Best implementation: georgeani/NetFlow-Forecasting-MGAE (0 stars, last commit 2026-06-12).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

georgeani/NetFlow-Forecasting-MGAECommunity25%

Code used for paper Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder

00Python, Jupyter NotebookApr 19, 20264 months ago
gmaegnnsnetflow

Similar Papers

Link Prediction for Flow-Driven Spatial Networks

85% match1 repo222023

Counterfactual Graph Transformer for Traffic Flow Prediction

83% match2023

Towards a graph-based foundation model for network traffic analysis

83% match2024

Dynamic Hypergraph Structure Learning for Traffic Flow Forecasting

82% match2023

Generalising Travel Time Prediction To Varying Route Choices In Urban Networks

82% match2026

Heterogeneous Graph Sequence Neural Networks for Dynamic Traffic Assignment

82% match2024

Cite this paper

@article{anyfantis2026forecasting,
  title  = {Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder},
  author = {Georgios Anyfantis and Pere Barlet-Ros},
  year   = {2026},
  eprint = {2604.20483},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2604.20483v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2604.20483.svg)](https://codeofpaper.com/paper/2604.20483)

Discussion