p-Meta: Towards On-device Deep Model Adaptation

TL;DR

p-Meta is a novel meta learning approach designed for efficient on-device deep model adaptation, enabling privacy-preserving, memory-efficient learning for IoT devices with improved accuracy and reduced memory usage.

Contribution

It introduces structure-wise partial parameter updates in meta learning, significantly reducing memory consumption while maintaining fast adaptation to new tasks.

Findings

Reduces peak dynamic memory by 2.5x on average.

Improves accuracy in few-shot image classification.

Enhances adaptation speed in reinforcement learning tasks.

Abstract

Data collected by IoT devices are often private and have a large diversity across users. Therefore, learning requires pre-training a model with available representative data samples, deploying the pre-trained model on IoT devices, and adapting the deployed model on the device with local data. Such an on-device adaption for deep learning empowered applications demands data and memory efficiency. However, existing gradient-based meta learning schemes fail to support memory-efficient adaptation. To this end, we propose p-Meta, a new meta learning method that enforces structure-wise partial parameter updates while ensuring fast generalization to unseen tasks. Evaluations on few-shot image classification and reinforcement learning tasks show that p-Meta not only improves the accuracy but also substantially reduces the peak dynamic memory by a factor of 2.5 on average compared to state-of-the-art few-shot adaptation methods.