ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization
Kaiwen Tang, Di Yu, Jiaqi Zheng, Changze Lv, Qianhui Liu + 2 more
TLDR
ShiftLIF is a new multi-level spiking neuron that uses power-of-two quantization for efficient, high-accuracy SNNs in edge sensing.
Key contributions
- Proposes ShiftLIF, a multi-level spiking neuron using logarithmically spaced power-of-two spike sets.
- Provides finer representation for densely concentrated small-amplitude membrane potentials.
- Enables multiplier-free synaptic computation via efficient bit-shift and accumulation operations.
- Achieves high accuracy on 10 datasets, matching or exceeding existing multi-level SNNs with low energy.
Why it matters
ShiftLIF significantly advances spiking neural networks for edge devices. It enables efficient, high-fidelity information transmission without costly multiplications, boosting SNN practicality and performance for energy-constrained sensing applications.
Original Abstract
Spiking neural networks (SNNs) are promising for edge sensing due to their event-driven computation and temporal filtering capability. However, standard leaky integrate-and-fire (LIF) neurons communicate only through binary spikes, which severely limit representational capacity. Existing multi-level spiking neurons improve information transmission, but often rely on uniform quantization that mismatches membrane-potential distributions or introduces costly synaptic multiplications. In this paper, we propose ShiftLIF, a multi-level spiking neuron that maps membrane potentials to a logarithmically spaced power-of-two spike set. This design provides finer representation in the small-amplitude regime, where membrane potentials are densely concentrated, while enabling multiplier-free synaptic computation through bit-shift and accumulation operations. As a result, ShiftLIF improves spike-level expressiveness without sacrificing the hardware-friendly nature of standard SNN computation. We evaluate ShiftLIF on 10 datasets spanning wireless, acoustic, motion, and visual sensing tasks. Results show that ShiftLIF consistently matches or exceeds the accuracy of existing multi-level spiking neurons while maintaining synaptic energy consumption close to standard binary LIF. These results indicate that ShiftLIF provides a favorable accuracy-efficiency trade-off for cross-modal edge sensing.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.