# SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network

arXiv: https://arxiv.org/abs/2510.03648 · HTML: https://mlsanity.com/paper/2510.03648/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 59 of its 88 references that are in the map.
- First posted on arXiv 4 Oct 2025.

## Builds on (most cited first, 30 of 59)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Introduction to Online Convex Optimization](https://mlsanity.com/paper/1909.05207/) (2019)
- [A Closer Look at Few-shot Classification](https://mlsanity.com/paper/1904.04232/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [Few-Shot Incremental Learning with Continually Evolved Classifiers](https://mlsanity.com/paper/2104.03047/) (2021)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning](https://mlsanity.com/paper/2006.06224/) (2020)
- [Mini-batch Stochastic Approximation Methods for Nonconvex Stochastic Composite Optimization](https://mlsanity.com/paper/1308.6594/) (2013)
- [Forward Compatible Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2203.06953/) (2022)
- [Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima](https://mlsanity.com/paper/2111.01549/) (2021)
- [Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization](https://mlsanity.com/paper/1805.10367/) (2018)
- [Attention Spiking Neural Networks](https://mlsanity.com/paper/2209.13929/) (2022)
- [Prototype Rectification for Few-Shot Learning](https://mlsanity.com/paper/1911.10713/) (2019)
- [A Theoretical and Empirical Comparison of Gradient Approximations in Derivative-Free Optimization](https://mlsanity.com/paper/1905.01332/) (2019)
- [MgSvF: Multi-Grained Slow vs. Fast Framework for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2006.15524/) (2020)
- [Few-Shot Lifelong Learning](https://mlsanity.com/paper/2103.00991/) (2021)
- [Subspace Regularizers for Few-Shot Class Incremental Learning](https://mlsanity.com/paper/2110.07059/) (2021)
- [SparCL: Sparse Continual Learning on the Edge](https://mlsanity.com/paper/2209.09476/) (2022)
- [Learning with Fantasy: Semantic-Aware Virtual Contrastive Constraint for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2304.00426/) (2023)
- [QKFormer: Hierarchical Spiking Transformer using Q-K Attention](https://mlsanity.com/paper/2403.16552/) (2024)
- [Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration](https://mlsanity.com/paper/2312.05229/) (2023)
- [A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays](https://mlsanity.com/paper/2110.10486/) (2021)
- [On the Soft-Subnetwork for Few-shot Class Incremental Learning](https://mlsanity.com/paper/2209.07529/) (2022)
- [Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks](https://mlsanity.com/paper/2302.14311/) (2023)

## Abstract (arXiv)

Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments. However, the scenario becomes particularly challenging when data samples are insufficient, requiring on-device few-shot class-incremental learning (FSCIL). Although existing work has explored parameter-efficient FSCIL frameworks based on artificial neural networks (ANNs), their deployment is still fundamentally constrained by limited device resources. Spiking neural networks (SNNs) process spatiotemporal information efficiently, offering lower energy consumption, greater biological plausibility, and compatibility with neuromorphic hardware than ANNs. In this work, we propose an SNN-based method containing Sparsity-Aware neuronal dynamics and Fast Adaptive structure (SAFA-SNN) for on-device FSCIL. By threshold regulation, most neurons exhibit stable spikes and others exhibit adaptive spikes. As a result, synaptic traces that encode base-class knowledge are naturally preserved, thereby alleviating catastrophic forgetting. To cope with spike non-differentiability in backpropagation, we employ a gradient-free technique, i.e., zeroth-order optimization. Moreover, class prototypes can limit overfitting on few-shot data but introduce bias. We enhance prototype discriminability by orthogonal subspace projection. Extensive experiments conducted on two standard benchmark datasets (CIFAR-100 and Mini-ImageNet) and three neuromorphic datasets (CIFAR10-DVS, DVS128 Gesture, and N-Caltech101) demonstrate that SAFA-SNN outperforms baselines, specifically achieving at least 4.01% improvement at the last incremental session on Mini-ImageNet and 20% lower energy cost on CIFAR-100 over baselines with practical implementation.