Topological Network Traffic Compression

The surge in computer network traffic, fueled by emerging applications and technology advancements, is creating a pressing need for efficient techniques to store and analyze massive traffic traces. This paper introduces a novel approach to address this challenge by employing Topological Deep Learning (TDL) for lossy traffic compression. Unlike Graph Neural Networks (GNNs), which rely on the binary interactions and local neighborhoods defined by graph representations, TDL methods can naturally accommodate higher-order relations among arbitrary network elements, thus offering more expressive representations beyond the graph domain. In particular, our proposed traffic compression framework aims to detect higher-order correlated structures within traffic data and employs Topological Neural Networks to generate compressed representations within these sets. This work assesses if this approach can outperform conventional Machine Learning (ML) compression architectures by better exploiting multi-datapoint interactions, potentially capturing correlations between distant network elements. We evaluate our method on two real-world networking datasets, comparing it against GNN-based architectures and a Multi-Layer Perceptron autoencoder designed for this task. The results demonstrate significant improvements w.r.t. ML baselines --from 30% up to 90% better reconstruction errors across all scenarios--, establishing our topological framework as a strong baseline for lossy neural traffic compression.