# PRIOT: Pruning-Based Integer-Only Transfer Learning for Embedded Systems

arXiv: https://arxiv.org/abs/2503.16860 · HTML: https://mlsanity.com/paper/2503.16860/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 12 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Builds on (most cited first, 8 of 8)

- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [What's Hidden in a Randomly Weighted Neural Network?](https://mlsanity.com/paper/1911.13299/) (2019)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Efficient Domain Generalization via Common-Specific Low-Rank Decomposition](https://mlsanity.com/paper/2003.12815/) (2020)
- [Training and Inference with Integers in Deep Neural Networks](https://mlsanity.com/paper/1802.04680/) (2018)
- [Learning to Generalize across Domains on Single Test Samples](https://mlsanity.com/paper/2202.08045/) (2022)
- [NITI: Training Integer Neural Networks Using Integer-only Arithmetic](https://mlsanity.com/paper/2009.13108/) (2020)
- [Addressing Gap between Training Data and Deployed Environment by On-Device Learning](https://mlsanity.com/paper/2203.01077/) (2022)

## Abstract (arXiv)

On-device transfer learning is crucial for adapting a common backbone model to the unique environment of each edge device. Tiny microcontrollers, such as the Raspberry Pi Pico, are key targets for on-device learning but often lack floating-point units, necessitating integer-only training. Dynamic computation of quantization scale factors, which is adopted in former studies, incurs high computational costs. Therefore, this study focuses on integer-only training with static scale factors, which is challenging with existing training methods. We propose a new training method named PRIOT, which optimizes the network by pruning selected edges rather than updating weights, allowing effective training with static scale factors. The pruning pattern is determined by the edge-popup algorithm, which trains a parameter named score assigned to each edge instead of the original parameters and prunes the edges with low scores before inference. Additionally, we introduce a memory-efficient variant, PRIOT-S, which only assigns scores to a small fraction of edges. We implement PRIOT and PRIOT-S on the Raspberry Pi Pico and evaluate their accuracy and computational costs using a tiny CNN model on the rotated MNIST dataset and the VGG11 model on the rotated CIFAR-10 dataset. Our results demonstrate that PRIOT improves accuracy by 8.08 to 33.75 percentage points over existing methods, while PRIOT-S reduces memory footprint with minimal accuracy loss.