Lossy Compression of Network Feature Data: When Less Is Enough

2026-02-25

AI Summary

This work addresses the challenge of high storage overhead from network feature data, which hinders scalability in large-scale core networks and resource-constrained IoT environments. The authors propose elevating compression to a first-class design dimension in network monitoring systems by introducing a task-aware lossy compression approach. This method substantially reduces storage requirements while preserving high accuracy for downstream analytical tasks such as website classification and device identification. By employing a semantics-preserving compression strategy, the study achieves a stable trade-off between storage efficiency and task performance across both core network and IoT scenarios, demonstrating the effectiveness and practicality of the compressed features for real-world applications.

Technology Category

• Data Mining & Knowledge Management: Data Compression
• Machine Learning: Learning on the Edge & Model Compression
• Application Domains: Internet of Things, Sensor Networks & Smart Cities

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Web Mining and Content Analysis: Web measurements
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Network traffic analysis increasingly relies on feature-based representations to support monitoring and security in the presence of pervasive encryption. Although features are more compact than raw packet traces, their storage has become a scalability bottleneck from large-scale core networks to resource-constrained Internet of Things (IoT) environments. This article investigates task-aware lossy compression strategies that reduce the storage footprint of traffic features while preserving analytics accuracy. Using website classification in core networks and device identification in IoT environments as representative use cases, we show that simple, semantics-preserving compression techniques expose stable operating regions that balance storage efficiency and task performance. These results highlight compression as a first-class design dimension in scalable network monitoring systems.

Problem

• lossy compression
• network feature data
• storage scalability
• traffic analysis
• task-aware compression

Innovation

• lossy compression
• network feature data
• task-aware compression
• scalable monitoring
• semantics-preserving