STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908795508097024 |
|---|---|
| author | Gianferrari, Matteo Moussadek, Omayma Salami, Riccardo Fiorini, Cosimo Tartarini, Lorenzo Gandolfi, Daniela Calderara, Simone |
| author_facet | Gianferrari, Matteo Moussadek, Omayma Salami, Riccardo Fiorini, Cosimo Tartarini, Lorenzo Gandolfi, Daniela Calderara, Simone |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_20870 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network Gianferrari, Matteo Moussadek, Omayma Salami, Riccardo Fiorini, Cosimo Tartarini, Lorenzo Gandolfi, Daniela Calderara, Simone Neural and Evolutionary Computing Artificial Intelligence Machine Learning 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. |
| title | STAER: Temporal Aligned Rehearsal for Continual Spiking Neural Network |
| topic | Neural and Evolutionary Computing Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2601.20870 |