重新审视 SNN 在线训练与部署：基于混合驱动 LIF 模型的梯度一致学习
Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model
HD-LIF 通过在上、下阈值区域采用不同的脉冲计算机制，把时序梯度分离并缓解替代梯度错位，为视觉任务中 SNN 的在线训练提供了一条在精度、显存占用与功耗之间取得平衡的路径；做低功耗视觉骨干或事件相机后端的研究者可直接替换 LIF 单元复用该机制。
原文依据 we propose Hybrid-Driven Leaky Integrate-and-Fire (HD-LIF) model family for efficient online learning
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论脉冲神经网络（SNN）因其类脑与高能效特性，被认为在人工智能的未来发展中具有巨大潜力。与传统的时空反向传播（STBP）训练方法相比，在线训练能够有效规避 GPU 显存爆炸的风险。然而，现有的在线学习框架无法解决前向与反向过程之间的梯度不一致问题，仅以优化 GPU 显存为目标，导致其在推理阶段相比基于 STBP 的模型并无性能优势。为应对上述挑战，我们提出了混合驱动泄漏积分发放（HD-LIF）模型族以支持高效在线学习，该模型在发放阈值的上区域与下区域分别采用不同的脉冲计算机制。我们从理论上指出，该学习框架能够有效分离时序梯度并解决替代梯度的错位问题，同时实现对学习精度、显存占用与功耗的全阶段优化。实验结果表明，我们的方案能够在多项评测指标上取得最优性能，突破了 SNN 在线训练与部署的传统范式。代码已开源至 https://github.com/hzc1208/HD_LIF。
英文原文摘要 1429 字符
Spiking Neural Networks (SNNs) are considered to have enormous potential in the future development of Artificial Intelligence due to their brain-inspired and energy-efficient properties. Compared to vanilla Spatial-Temporal Back-propagation (STBP) training methods, online training can effectively avoid the risk of GPU memory explosion. However, current online learning frameworks cannot tackle the gradient discrepancy problem between the forward and backward process, merely aiming to optimize the GPU memory, resulting in no performance advantages compared to the STBP-based models in the inference stage. To address the aforementioned challenges, we propose Hybrid-Driven Leaky Integrate-and-Fire (HD-LIF) model family for efficient online learning, which respectively adopt different spiking calculation mechanism in the upper-region and lower-region of the firing threshold. We theoretically point out that our learning framework can effectively separate temporal gradients and address the misalignment problem of surrogate gradients, as well as achieving full-stage optimization towards learning precision, memory footprint and power consumption. Experimental results have demonstrated that our scheme is enable to achieve state-of-the-art performance for multiple evaluation metrics, breaking through the traditional paradigm of SNN online training and deployment. Code is available at https://github.com/hzc1208/HD_LIF.