AI Paper Atlas

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

HO-SFL: Hybrid-Order Split Federated Learning with Backprop-Free Clients and Dimension-Free Aggregation

Qiyuan Chen, Xian Wu, Yi Wang, Xianhao Chen

ICML 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
replace client-side BP with hybrid-order ZO using server activation gradientsSFL · CIFAR-10 IIDvalidation accuracy: marginal gap to SFLNo clear effect
use HO-SFL instead of SFL in Non-IID settingSFL · CIFAR-10 Non-IIDvalidation accuracyImproved
add server-supplied activation gradients to client ZOZO-SFL · GLUE (LLaMA-3.2-1B) SST2accuracy (%): 61.5 -> 93.9Improved
hybrid-order instead of first-order SplitLoRASplitLoRA · GLUE RTE (LLaMA-3.2-1B)accuracy (%): 70.0 -> 73.3Improved
hybrid-order instead of first-order SplitLoRASplitLoRA · GLUE WSC (OPT-125M)accuracy (%): 64.4 -> 60.6Hurt
scale model from 125M to 8BHO-SFL · SQuADF1: 0.9413 vs 0.9389 for Qwen3-8BNo clear effect
dimension-free scalar aggregation instead of model uploadSFL · CIFAR-10 IIDcommunication cost (GB): 4.20 -> 2.44Improved
eliminate client-side BPSFL · LLaMA-3.2-1B SST-2 LoRAclient peak memory (GB): 8.78 -> 4.14Improved
increase client-side layers from 2 to 8 (ablation)HO-SFL · LLaMA-3.2-1Bconvergence speed: marginal reductionHurt
increase perturbation count P (ablation)HO-SFL · ResNet-18performance: monotonic improvementImproved
choose smoothing parameter mu too large or too small (ablation)HO-SFL · ablationapproximation qualityMixed

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.

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

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