Research
Forecasting Individual NetFlows using a Predictive Masked Graph Autoencoder
arXiv:2604.20483v1 Announce Type: cross Abstract: In this paper, we propose a proof-of-concept Graph Neural Network model that can successfully predict network flow-level traffic (NetFlow) by accurate
arXiv:2604.20483v1 Announce Type: cross 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.
Related
- FlowRefiner: Flow Matching-Based Iterative Refinement for 3D Turbulent Flow Simulation
- XANE(3): An E(3)-Equivariant Graph Neural Network for Accurate Prediction of XANES Spectra from Atomic Structures
- A Bipartite Graph Approach to U.S.-China Cross-Market Return Forecasting
- Improving DNS Exfiltration Detection via Transformer Pretraining
- Geminet: Learning the Duality-based Iterative Process for Lightweight Traffic Engineering in Changing Topologies
Source: arXiv cs.LG | 2026-04-23