AI Paper Atlas

Research map / Federated learning and privacy / Communication-efficient FL

SFedHIFI: Fire Rate-Based Heterogeneous Information Fusion for Spiking Federated Learning

Ran Tao, Qiugang Zhan, Shantian Yang, Xiurui Xie, Qi Tian, Guisong Liu

AAAI 2026 · Federated learning and privacy › Communication-efficient FL · approach: Communication-efficient heterogeneous FL · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
add HIFI fusion module (ablation)SFedHIFI · CIFAR-10 Dir(0.3)avg top-1 accuracy: 78.16 -> 84.73Improved
add HIFI fusion module (ablation)SFedHIFI · CIFAR-10 IIDavg top-1 accuracy: 88.71 -> 89.62Improved
select fusion layer by firing rate instead of random layer (ablation)SFedHIFI · CIFAR-10 Dir(0.3)avg top-1 accuracy: 67.48 -> 84.73Improved
select fusion layer by firing rate instead of fixed last conv layer (ablation)SFedHIFI · CIFAR-10 Dir(0.3)avg top-1 accuracy: 79.45 -> 84.73Improved
select fusion layer by firing rate instead of fixed last conv layer (ablation)SFedHIFI · CIFAR-10 IIDavg top-1 accuracy: 88.52 -> 89.62Improved
random-layer fusion vs no fusion (ablation)SFedHIFI · CIFAR-10 Dir(0.3)avg top-1 accuracy: 78.16 -> 67.48Hurt
cross-scale aggregation (SFedHIFI) vs same-scale baselinesSNN FL · CIFAR-100 Dir(0.5)avg top-1 accuracy: 21.42 -> 33.00Improved
cross-scale aggregation (SFedHIFI) vs same-scale baselinesSNN FL · CIFAR-10 Dir(0.3)avg top-1 accuracy: 74.49 -> 84.73Improved
cross-scale aggregation (SFedHIFI) vs same-scale baselinesSNN FL · CIFAR-100 IIDavg top-1 accuracy: 39.08 -> 39.20Improved
cross-scale aggregation (SFedHIFI) vs same-scale baselinesSNN FL · Fashion-MNIST Dir(0.3)avg top-1 accuracy: 88.41 -> 88.43No clear effect
replace ANN with SNN (SFedHIFI)SFedHIFI · Fashion-MNISTavg energy (x10^-3 mJ): 90.917 -> 51.148Improved
replace ANN with SNN (SFedHIFI)SFedHIFI · Fashion-MNIST Dir(0.3)avg top-1 accuracy: 91.06 -> 88.43Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy