# Predictive Suppression Layers for Communication-Efficient Spiking Neural Networks

arXiv: https://arxiv.org/abs/2609.21583 · HTML: https://mlsanity.com/paper/2609.21583/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 16 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 5 of 5)

- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Adaptive Computation Time for Recurrent Neural Networks](https://mlsanity.com/paper/1603.08983/) (2016)
- [Converting Static Image Datasets to Spiking Neuromorphic Datasets Using Saccades](https://mlsanity.com/paper/1507.07629/) (2015)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)

## Abstract (arXiv)

Feedforward Spiking Neural Networks (SNNs) typically propagate every generated spike indiscriminately, disregarding whether the information is redundant from an information-theoretic perspective. This lack of selectivity induces high redundancy in inter-layer communication, creating an expensive overhead, e.g., in scenarios involving many-core neuromorphic hardware or communication-dominated Internet-of-Things (IoT) where features are transmitted wirelessly. To address this challenge, we trade localized processing for leaner network channels by introducing a minimal predictive coding framework for SNNs. We propose two layer variants sharing a predictor block: error units, which transmit signed spiking residuals, and predictive suppression, which uses residual magnitude to dynamically gate and forward only unpredictable, "surprising" activity. Evaluated on the N-MNIST and Spiking Heidelberg Digits (SHD) datasets using diagnostic metrics that decouple local processing from cross-layer communication, our new predictive coding layers achieve significant communication savings. Numerical results reveal a three-fold reduction in communicated activity, while increasing the task accuracy for both datasets. The latter finding is notable, and suggests that predictive coding layers not only minimize communication overhead, but also produce output feature vectors with a higher representation power.