Research map / Architectures and efficiency / Spiking networks
A Brain-Inspired Gating Mechanism Unlocks Robust Computation in Spiking Neural Networks
Qianyi Bai, Haiteng Wang, Qiang Yu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace LIF neuron with DGN (dynamic conductance gating), feedforward | SNN · TIDIGITS under additive noise | accuracy (%): 46.83 -> 95.34 | Improved |
| replace LIF neuron with DGN, recurrent, under PGD attack | SNN · SHD under PGD attack | accuracy (%): 30.59 -> 66.13 | Improved |
| replace LIF neuron with DGN, feedforward, clean | SNN · SHD | accuracy (%): 77.30 -> 85.18 | Improved |
| replace LIF neuron with DGN, feedforward, PGD attack | SNN · TIDIGITS under PGD attack | accuracy (%): 15.39 -> 86.76 | Improved |
| use recurrent DGN instead of LSTM, clean | recurrent SNN · SHD | accuracy (%): 89.20 -> 87.78 | Hurt |
| use recurrent DGN instead of TC-LIF, clean | recurrent SNN · SHD | accuracy (%): 88.91 -> 87.78 | Hurt |
| use recurrent DGN instead of LSTM under subtractive noise | recurrent SNN · SHD under subtractive noise | accuracy (%): 64.58 -> 61.91 | Hurt |
| use recurrent DGN instead of LSTM under additive noise | recurrent SNN · TIDIGITS under additive noise | accuracy (%): 65.12 -> 94.84 | Improved |
| use recurrent DGN instead of LSTM, clean | recurrent SNN · Ti46Alpha | accuracy (%): 96.05 -> 96.31 | No clear effect |
| use feedforward DGN instead of TC-LIF | feedforward SNN · SSC | accuracy (%): 63.46 -> 67.54 | Improved |
| use DGN instead of LSTM under PGD on recurrent SHD | recurrent · SHD under PGD attack | accuracy (%): 32.01 -> 66.13 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- TC-LIF (128-128) — TC-LIF: A Two-Compartment Spiking Neuron Model for Long-Term Sequential Modelling (AAAI 2024) · better on 2 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Neuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks (NeurIPS 2026 · similarity 0.89)
- FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor (NeurIPS 2024 · similarity 0.89)
- Enhancing the Robustness of Spiking Neural Networks with Stochastic Gating Mechanisms (AAAI 2024 · similarity 0.89)
- Robust Stable Spiking Neural Networks (ICML 2024 · similarity 0.87)
- Autaptic Synaptic Circuit Enhances Spatio-temporal Predictive Learning of Spiking Neural Networks (ICML 2024 · similarity 0.87)
- The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural Networks (NeurIPS 2026 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
