# Automating In-Network Machine Learning

arXiv: https://arxiv.org/abs/2205.08824 · HTML: https://mlsanity.com/paper/2205.08824/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 76 references that are in the map.
- First posted on arXiv 18 May 2022.

## Builds on (most cited first, 10 of 10)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [Scaling Distributed Machine Learning with In-Network Aggregation](https://mlsanity.com/paper/1903.06701/) (2019)
- [Programming Protocol-Independent Packet Processors](https://mlsanity.com/paper/1312.1719/) (2013)
- [Filling gaps in trustworthy development of AI](https://mlsanity.com/paper/2112.07773/) (2021)
- [pForest: In-Network Inference with Random Forests](https://mlsanity.com/paper/1909.05680/) (2019)
- [PINT: Probabilistic In-band Network Telemetry](https://mlsanity.com/paper/2007.03731/) (2020)
- [Running Neural Networks on the NIC](https://mlsanity.com/paper/2009.02353/) (2020)
- [In-network Neural Networks](https://mlsanity.com/paper/1801.05731/) (2018)
- [IIsy: Practical In-Network Classification](https://mlsanity.com/paper/2205.08243/) (2022)

## Abstract (arXiv)

Using programmable network devices to aid in-network machine learning has been the focus of significant research. However, most of the research was of a limited scope, providing a proof of concept or describing a closed-source algorithm. To date, no general solution has been provided for mapping machine learning algorithms to programmable network devices. In this paper, we present Planter, an open-source, modular framework for mapping trained machine learning models to programmable devices. Planter supports a wide range of machine learning models, multiple targets and can be easily extended. The evaluation of Planter compares different mapping approaches, and demonstrates the feasibility, performance, and resource efficiency for applications such as anomaly detection, financial transactions, and quality of experience. The results show that Planter-based in-network machine learning algorithms can run at line rate, have a negligible effect on latency, coexist with standard switching functionality, and have no or minor accuracy trade-offs.