解决脉冲网络持续学习中的遗忘与时序错位问题。
STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network
- 用可微分的软DTW损失保持脉冲时间结构一致。
- 在ResNet19上实现序列MNIST和CIFAR10的最优性能。
- 适合追求生物可解释性持续学习的研究者。
脉冲神经网络（SNN）因事件驱动的时间动态特性，天然适合持续学习；但其在类增量学习（CIL）中的应用受限于灾难性遗忘及脉冲模式的时间错位。本文提出脉冲时间对齐经验回放框架（STAER），通过可微分的软DTW对齐损失显式保留时间结构，提升表征稳定性，并采用输出逻辑的时空伸缩机制强化学习能力。基于深度ResNet19脉冲骨干网络，在序列MNIST和序列CIFAR10上达到当前最优性能，表现匹配或超越强健的ANN基线（如ER、DER++），同时保持生物合理动力学。消融实验验证了显式时间对齐对表征稳定性的关键作用，证明STAER是面向脉冲原生终身学习的可扩展方案。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。