# MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption

arXiv: https://arxiv.org/abs/2302.12347 · HTML: https://mlsanity.com/paper/2302.12347/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 23 Feb 2023.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Constrained Few-shot Class-incremental Learning](https://mlsanity.com/paper/2203.16588/) (2022)
- [Machine Learning at the Network Edge: A Survey](https://mlsanity.com/paper/1908.00080/) (2019)
- [Overcoming Data Limitation in Medical Visual Question Answering](https://mlsanity.com/paper/1909.11867/) (2019)
- [TinyOL: TinyML with Online-Learning on Microcontrollers](https://mlsanity.com/paper/2103.08295/) (2021)
- [Classification using Hyperdimensional Computing: A Review](https://mlsanity.com/paper/2004.11204/) (2020)
- [Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learning](https://mlsanity.com/paper/2012.08677/) (2020)
- [Understanding Hyperdimensional Computing for Parallel Single-Pass Learning](https://mlsanity.com/paper/2202.04805/) (2022)
- [What Matters For Meta-Learning Vision Regression Tasks?](https://mlsanity.com/paper/2203.04905/) (2022)
- [LeHDC: Learning-Based Hyperdimensional Computing Classifier](https://mlsanity.com/paper/2203.09680/) (2022)
- [Hypervector Design for Efficient Hyperdimensional Computing on Edge Devices](https://mlsanity.com/paper/2103.06709/) (2021)
- [When Low Resource NLP Meets Unsupervised Language Model: Meta-pretraining Then Meta-learning for Few-shot Text Classification](https://mlsanity.com/paper/1908.08788/) (2019)
- [Generalized Learning Vector Quantization for Classification in Randomized Neural Networks and Hyperdimensional Computing](https://mlsanity.com/paper/2106.09821/) (2021)
- [A Brain-Inspired Low-Dimensional Computing Classifier for Inference on Tiny Devices](https://mlsanity.com/paper/2203.04894/) (2022)
- [In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory](https://mlsanity.com/paper/2207.06810/) (2022)
- [Visual Perception Generalization for Vision-and-Language Navigation via Meta-Learning](https://mlsanity.com/paper/2012.05446/) (2020)
- [Feed-Forward On-Edge Fine-tuning Using Static Synthetic Gradient Modules](https://mlsanity.com/paper/2009.09675/) (2020)

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

- [A Machine Learning-oriented Survey on Tiny Machine Learning](https://mlsanity.com/paper/2309.11932/) (2023)
- [On-device Online Learning and Semantic Management of TinyML Systems](https://mlsanity.com/paper/2405.07601/) (2024)
- [Scheduled Knowledge Acquisition on Lightweight Vector Symbolic Architectures for Brain-Computer Interfaces](https://mlsanity.com/paper/2403.13844/) (2024)

## Abstract (arXiv)

Fast model updates for unseen tasks on intelligent edge devices are crucial but also challenging due to the limited computational power. In this paper,we propose MetaLDC, which meta-trains braininspired ultra-efficient low-dimensional computing classifiers to enable fast adaptation on tiny devices with minimal computational costs. Concretely, during the meta-training stage, MetaLDC meta trains a representation offline by explicitly taking into account that the final (binary) class layer will be fine-tuned for fast adaptation for unseen tasks on tiny devices; during the meta-testing stage, MetaLDC uses closed-form gradients of the loss function to enable fast adaptation of the class layer. Unlike traditional neural networks, MetaLDC is designed based on the emerging LDC framework to enable ultra-efficient on-device inference. Our experiments have demonstrated that compared to SOTA baselines, MetaLDC achieves higher accuracy, robustness against random bit errors, as well as cost-efficient hardware computation.