Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.09809 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908704780058624 |
|---|---|
| author | Zhu, Di Chen, Jianxi Kim, Hyojoon |
| author_facet | Zhu, Di Chen, Jianxi Kim, Hyojoon |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_09809 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Practical and Usable In-network Classification Zhu, Di Chen, Jianxi Kim, Hyojoon Networking and Internet Architecture 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. |
| title | Towards Practical and Usable In-network Classification |
| topic | Networking and Internet Architecture |
| url | https://arxiv.org/abs/2512.09809 |