STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network
This addresses the problem of enabling SNNs for lifelong learning in AI applications, though it is incremental as it builds on existing rehearsal methods with novel temporal alignment.
The paper tackles catastrophic forgetting and temporal misalignment in Spiking Neural Networks (SNNs) for Class-Incremental Learning (CIL) by introducing STAER, a framework that preserves temporal structure, achieving state-of-the-art performance on Sequential-MNIST and Sequential-CIFAR10 and matching or outperforming ANN baselines.
Spiking Neural Networks (SNNs) are inherently suited for continuous learning due to their event-driven temporal dynamics; however, their application to Class-Incremental Learning (CIL) has been hindered by catastrophic forgetting and the temporal misalignment of spike patterns. In this work, we introduce Spiking Temporal Alignment with Experience Replay (STAER), a novel framework that explicitly preserves temporal structure to bridge the performance gap between SNNs and ANNs. Our approach integrates a differentiable Soft-DTW alignment loss to maintain spike timing fidelity and employs a temporal expansion and contraction mechanism on output logits to enforce robust representation learning. Implemented on a deep ResNet19 spiking backbone, STAER achieves state-of-the-art performance on Sequential-MNIST and Sequential-CIFAR10. Empirical results demonstrate that our method matches or outperforms strong ANN baselines (ER, DER++) while preserving biologically plausible dynamics. Ablation studies further confirm that explicit temporal alignment is critical for representational stability, positioning STAER as a scalable solution for spike-native lifelong learning. Code is available at https://github.com/matteogianferrari/staer.