AI Paper Atlas

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

No Retraining at Edge: Efficient Resource-Aware Mixed-Precision Quantization via Federated Supernet Learning

Lianbo Ma, Yonghui Su, Nan Li, Xingwei Wang

ICML 2026 · Federated learning and privacy › Communication-efficient FL · approach: Communication-efficient heterogeneous FL

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
apply layer-wise semantic aggregation weights instead of hybrid (ablation)DFMPQ SAHA · Tiny-ImageNet (alpha=0.5)test accuracy (%): 66.65 -> 63.70Hurt
use hybrid semantic-aware aggregation instead of FedAvg (ablation)DFMPQ · CIFAR-100 (alpha=0.5)test accuracy (%): 70.69 -> 70.88Improved
use hybrid semantic-aware aggregation instead of FedAvg (ablation)DFMPQ · CIFAR-10 (alpha=0.5)test accuracy (%): 90.42 -> 90.71No clear effect
use hybrid instead of stage-wise aggregation (ablation)DFMPQ · CIFAR-10 (alpha=0.5)test accuracy (%): 90.92 -> 90.71No clear effect
add CCSA regularization (lambda=0 -> 0.1) (ablation)DFMPQ mixed-precision ResNet18 · CIFAR-10, CIFAR-100, Tiny-ImageNet (alpha=0.5)test accuracyImproved
increase CCSA lambda above 0.1 (ablation)DFMPQ · CIFAR-10, CIFAR-100, Tiny-ImageNet (alpha=0.5)test accuracyHurt
use 3-bit mixed-precision supernet instead of retrained quantized baselinesDFMPQ vs FedMPQ · CIFAR-10 (alpha=0.5)test accuracy (%): 67.10 -> 80.24Improved
3-bit mixed-precision DFMPQ versus full-precision FedWSDFMPQ · CIFAR-10 (alpha=0.5)test accuracy (%): 91.0 -> 80.24Hurt
increase number of clients from 10 to 40DFMPQ · CIFAR-100 (alpha=0.5)test accuracy (%): 64.15 -> 36.64Hurt

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