# IIsy: Practical In-Network Classification

arXiv: https://arxiv.org/abs/2205.08243 · HTML: https://mlsanity.com/paper/2205.08243/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 64 references that are in the map.
- First posted on arXiv 17 May 2022.

## Builds on (most cited first, 11 of 11)

- [In-Datacenter Performance Analysis of a Tensor Processing Unit](https://mlsanity.com/paper/1704.04760/) (2017)
- [Adaptive Federated Learning in Resource Constrained Edge Computing Systems](https://mlsanity.com/paper/1804.05271/) (2018)
- [Scaling Distributed Machine Learning with In-Network Aggregation](https://mlsanity.com/paper/1903.06701/) (2019)
- [FINN-R: An End-to-End Deep-Learning Framework for Fast Exploration of Quantized Neural Networks](https://mlsanity.com/paper/1809.04570/) (2018)
- [Programming Protocol-Independent Packet Processors](https://mlsanity.com/paper/1312.1719/) (2013)
- [Taurus: A Data Plane Architecture for Per-Packet ML](https://mlsanity.com/paper/2002.08987/) (2020)
- [pForest: In-Network Inference with Random Forests](https://mlsanity.com/paper/1909.05680/) (2019)
- [Bayesian Optimization with Machine Learning Algorithms Towards Anomaly Detection](https://mlsanity.com/paper/2008.02327/) (2020)
- [Running Neural Networks on the NIC](https://mlsanity.com/paper/2009.02353/) (2020)
- [RADE: Resource-Efficient Supervised Anomaly Detection Using Decision Tree-Based Ensemble Methods](https://mlsanity.com/paper/1909.11877/) (2019)
- [Heavy-Hitter Detection Entirely in the Data Plane](https://mlsanity.com/paper/1611.04825/) (2016)

## Built on by (most cited first, 3 of 3)

- [Brain-on-Switch: Towards Advanced Intelligent Network Data Plane via NN-Driven Traffic Analysis at Line-Speed](https://mlsanity.com/paper/2403.11090/) (2024)
- [Automating In-Network Machine Learning](https://mlsanity.com/paper/2205.08824/) (2022)
- [INSIGHT: A Survey of In-Network Systems for Intelligent, High-Efficiency AI and Topology Optimization](https://mlsanity.com/paper/2505.24269/) (2025)

## Abstract (arXiv)

The rat race between user-generated data and data-processing systems is currently won by data. The increased use of machine learning leads to further increase in processing requirements, while data volume keeps growing. To win the race, machine learning needs to be applied to the data as it goes through the network. In-network classification of data can reduce the load on servers, reduce response time and increase scalability. In this paper, we introduce IIsy, implementing machine learning classification models in a hybrid fashion using off-the-shelf network devices. IIsy targets three main challenges of in-network classification: (i) mapping classification models to network devices (ii) extracting the required features and (iii) addressing resource and functionality constraints. IIsy supports a range of traditional and ensemble machine learning models, scaling independently of the number of stages in a switch pipeline. Moreover, we demonstrate the use of IIsy for hybrid classification, where a small model is implemented on a switch and a large model at the backend, achieving near optimal classification results, while significantly reducing latency and load on the servers.