CATO: End-to-End Optimization of ML-Based Traffic Analysis Pipelines

TL;DR

CATO is a framework that jointly optimizes ML-based network traffic analysis pipelines for both predictive accuracy and system efficiency, enabling deployment with significantly reduced latency and higher throughput.

Contribution

It introduces a multi-objective Bayesian optimization approach to automatically generate end-to-end optimized traffic analysis pipelines that balance accuracy and system costs.

Findings

Up to 3600x lower inference latency

3.7x higher zero-loss throughput

Better model performance compared to feature optimization techniques

Abstract

Machine learning has shown tremendous potential for improving the capabilities of network traffic analysis applications, often outperforming simpler rule-based heuristics. However, ML-based solutions remain difficult to deploy in practice. Many existing approaches only optimize the predictive performance of their models, overlooking the practical challenges of running them against network traffic in real time. This is especially problematic in the domain of traffic analysis, where the efficiency of the serving pipeline is a critical factor in determining the usability of a model. In this work, we introduce CATO, a framework that addresses this problem by jointly optimizing the predictive performance and the associated systems costs of the serving pipeline. CATO leverages recent advances in multi-objective Bayesian optimization to efficiently identify Pareto-optimal configurations, and automatically compiles end-to-end optimized serving pipelines that can be deployed in real networks. Our evaluations show that compared to popular feature optimization techniques, CATO can provide up to 3600x lower inference latency and 3.7x higher zero-loss throughput while simultaneously achieving better model performance.