提出DEP方法，让脉冲神经网络更抗数据差异干扰。
Towards Robust Spiking Neural Networks:Mitigating Heterogeneous Training Vulnerability via Dominant Eigencomponent Projection
- 通过正交投影移除梯度主成分，抑制网络坍塌
- 使脉冲网络在异构数据下仍保持稳定，避免梯度爆炸
- 无需调参，适合对鲁棒性要求高的实际部署场景
脉冲神经网络（SNN）以离散脉冲处理信息，能实现极低能耗运行。然而实验发现，采用主流的直接编码结合时间反向传播（BPTT）训练时，仅一次来自分布稍有差异的数据后向传播，即可能导致网络灾难性崩溃。理论分析表明，该脆弱性源于直接编码中的重复输入与BPTT的梯度累积特性，共同导致海森矩阵谱半径异常增大。为此，我们提出一种无需超参数调节的方法——主导特征成分投影（DEP）。通过正交投影精确去除梯度的主导分量，有效降低海森矩阵谱半径，防止网络陷入尖锐极小值。大量实验表明，DEP不仅显著缓解了SNN对异构数据投毒的敏感性，还大幅提升了整体鲁棒性，优于多个关键基线，为SNN的安全可靠部署提供了有力支持。
原文摘要 · Abstract (English)
Spiking Neural Networks (SNNs) process information via discrete spikes, enabling them to operate at remarkably low energy levels. However, our experimental observations reveal a striking vulnerability when SNNs are trained using the mainstream method--direct encoding combined with backpropagation through time (BPTT): even a single backward pass on data drawn from a slightly different distribution can lead to catastrophic network collapse. Our theoretical analysis attributes this vulnerability to the repeated inputs inherent in direct encoding and the gradient accumulation characteristic of BPTT, which together produce an exceptional large Hessian spectral radius. To address this challenge, we develop a hyperparameter-free method called Dominant Eigencomponent Projection (DEP). By orthogonally projecting gradients to precisely remove their dominant components, DEP effectively reduces the Hessian spectral radius, thereby preventing SNNs from settling into sharp minima. Extensive experiments demonstrate that DEP not only mitigates the vulnerability of SNNs to heterogeneous data poisoning, but also significantly enhances overall robustness compared to key baselines, providing strong support for safer and more reliable SNN deployment.
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。