AI Paper Atlas

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

Federated Active Learning Under Extreme Non-IID and Global Class Imbalance

Chen-Chen Zong, Sheng-Jun Huang

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 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
use adaptively selected query model instead of the complementary one (ablation)FairFAL · ε=0.1, imbalance 20final test accuracy (%): 58.49 -> 59.33Improved
use adaptively selected query model instead of the complementary one (ablation)FairFAL · ε=100, imbalance 20final test accuracy (%): 61.89 -> 63.65Improved
build prototypes from global features instead of local features (ablation)FairFAL · ε=0.1, imbalance 20final test accuracy (%): 59.14 -> 59.95Improved
build prototypes from global features instead of local features (ablation)FairFAL · ε=100, imbalance 20final test accuracy (%): 63.39 -> 64.02Improved
add two-stage uncertainty-diversity sampling (alpha=4) after class-wise sampling (ablation)FairFAL · ε=0.1, imbalance 20final test accuracy (%): 59.95 -> 60.44Improved
vary candidate pool ratio alpha among 2, 3, 4 (ablation)FairFAL · ε=0.1 and ε=100, imbalance 20final test accuracy (%): 60.61 / 60.38 / 60.44No clear effect
query with global model vs local model under Entropy, homogeneous clients with severe imbalance (ε=100, imbalance 20)Entropy sampling · CIFAR-10AULC: +106 ppImproved
query with global model vs local model under Entropy, heterogeneous clients (ε=0.1, imbalance 1)Entropy sampling · CIFAR-10AULC: local wins by 201 ppHurt
use global model rather than local for Coreset samplingCoreset sampling · CIFAR-10AULC: +21 to +92 ppImproved
FairFAL vs best baseline on OctMNISTFairFAL · OctMNIST (ε=0.1)test accuracy (%): 70.40 -> 72.80Improved

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