A Closer Look at Knowledge Distillation in Spiking Neural Network Training

Xu Liu; Na Xia; Jinxing Zhou; Jingyuan Xu; Dan Guo

AAAI 2026technical0 citations

A Closer Look at Knowledge Distillation in Spiking Neural Network Training

Xu Liu, Na Xia, Jinxing Zhou, Jingyuan Xu, Dan Guo

Abstract

Spiking Neural Networks (SNNs) become popular due to excellent energy efficiency, yet facing challenges for effective model training. Recent works improve this by introducing knowledge distillation (KD) techniques, with the pre-trained artificial neural networks (ANNs) used as teachers and the target SNNs as students. This is commonly accomplished through a straightforward element-wise alignment of intermediate features and prediction logits from ANNs and SNNs, often neglecting the intrinsic differences between their architectures. Specifically, ANN

BibTeX

@inproceedings{aaai2026_acloserlookatkno,
  title = {A Closer Look at Knowledge Distillation in Spiking Neural Network Training},
  author = {Xu Liu and Na Xia and Jinxing Zhou and Jingyuan Xu and Dan Guo},
  booktitle = {AAAI 2026},
  year = {2026}
}