AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

FedHera: Towards Drift-Resilient Federated Fine-tuning with Heterogeneous Resources

Ke Xiao, Qiyuan Wang, Christos Anagnostopoulos, Zhuoran Tan, Wenhao Li

ICML 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning

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
decouple downloaded rank r_tot from trainable rank r_train with prefix gating (frozen tail) instead of coupled ranksFedHera vs FlexLoRA/FedHL · Alpaca (Skewed)evaluation loss: 1.186 (FedHL) -> 1.140Improved
decouple rank reception from trainingFedHera · E2E NLG (Skewed), Qwen3-0.6Babsolute drift: 2.991 (FlexLoRA) -> 2.060Improved
decoupling versus best coupled baseline FedHLFedHera · E2E NLG (Skewed), Qwen3-0.6Babsolute drift: 2.072 -> 2.060No clear effect
increase local epochs from 1 to 5 (ablation)FedHera · E2E NLG, Qwen3-0.6Brelative driftMixed
increase local epochs E from 1 to 7 for coupled baselines vs FedHera (ablation)FlexLoRA, FedHL, FedHeLLo · E2E NLGabsolute driftHurt
use energy-aware water-filling rank allocation instead of uniform or random allocation (ablation)FedHera · matched budgetsfidelityImproved
add Adaptive Tail Warm-up (ATW) for the frozen tail (ablation)FedHera · early roundstraining stabilityImproved
use standard aggregation instead of residual aggregation (ablation)FedHera · reasoning/generation tasksaccuracyNo clear effect
adapt all linear modules rather than a subset (ablation)FedHera · ablationperformanceImproved
use FedHeLLo (layer pruning heterogeneity) instead of rank-adaptive methodsbaseline · Alpaca (Skewed)evaluation loss: 1.186 (FedHL) vs 1.617Hurt

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