# Astrocyte-gated multi-timescale plasticity for online continual learning in deep spiking neural networks

## TL;DR

This paper introduces a new framework for deep spiking neural networks that enables efficient online learning by mimicking astrocyte regulation in the brain.

## Contribution

The novel Astrocyte-Gated Multi-Timescale Plasticity (AGMP) framework addresses the stability-plasticity dilemma in online continual learning.

## Key findings

- AGMP achieves competitive accuracy with offline BPTT while using constant memory complexity.
- AGMP outperforms state-of-the-art online learning rules in mitigating catastrophic forgetting without replay buffers.

## Abstract

Spiking Neural Networks (SNNs) offer a paradigm of energy-efficient, event-driven computation that is well-suited for processing asynchronous sensory streams. However, training deep SNNs robustly in an online and continual manner remains a formidable challenge. Standard Backpropagation-through-Time (BPTT) suffers from a prohibitive memory bottleneck due to the storage of temporal histories, while local plasticity rules often fail to balance the trade-off between rapid acquisition of new information and the retention of old knowledge (the stability-plasticity dilemma). Motivated by the tripartite synapse in biological systems, where astrocytes regulate synaptic efficacy over slow timescales, we propose Astrocyte-Gated Multi-Timescale Plasticity (AGMP). AGMP is a scalable, online learning framework that augments eligibility traces with a broadcast teaching signal and a novel astrocyte-mediated gating mechanism. This slow astrocytic variable integrates neuronal activity to dynamically modulate plasticity, suppressing updates in stable regimes while enabling adaptation during distribution shifts. We evaluate AGMP on a comprehensive suite of neuromorphic benchmarks, including N-Caltech101, DVS128 Gesture, and Spiking Heidelberg Digits (SHD). Experimental results demonstrate that AGMP achieves accuracy competitive with offline BPTT while maintaining constant O(1) temporal memory complexity. Furthermore, in rigorous Class-Incremental Continual Learning scenarios (e.g., Split CIFAR-100), AGMP significantly mitigates catastrophic forgetting without requiring replay buffers, outperforming state-of-the-art online learning rules. This work provides a biologically grounded, hardware-friendly path toward autonomous learning agents capable of lifelong adaptation.