Towards Practical and Usable In-network Classification

TL;DR

This paper introduces ACORN, a system that automates the deployment of machine learning models directly on network hardware, enabling real-time classification with improved capacity and minimal performance overhead.

Contribution

ACORN provides an automated, end-to-end pipeline for deploying ML models on network devices, supporting larger models and runtime programmability with a novel data plane representation.

Findings

ACORN deploys 2-4x more features than existing solutions.

ACORN imposes negligible overhead on network performance.

Prototype implemented in P4 on real hardware.

Abstract

In-network machine learning enables real-time classification directly on network hardware, offering consistently low inference latency. However, current solutions are limited by strict hardware constraints, scarce on-device resources, and poor usability, making them impractical for ML developers and cloud operators. To this end, we propose ACORN, an end-to-end system that automates the distributed deployment of practical machine learning models across the network. ACORN provides a fully automated pipeline that loads and deploys Python ML models on network devices using an optimized deployment plan from an ILP planner. To support larger models under hardware constraints and allow runtime programmability, ACORN adopts a novel data plane representation for Decision Tree, Random Forest, and Support Vector Machine models. We implement ACORN prototype in P4 and run it on real programmable hardware. Our evaluation shows ACORN can deploy classification ML models with 2-4x more features than state-of-the-art solutions, while imposing negligible overhead on network performance and traffic. We will make our data plane program, model translator, optimizer, and all related scripts publicly available.