AI Paper Atlas

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

FedRNC: Addressing Spatio-Temporal Label Misalignment in Federated Noisy Class-Incremental Learning

Xingwei Huang, Zhaobin Sun, Junjie Shi, Xin Yang, Zengqiang Yan

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 2 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 prototype-guided relabeling (stage 2) after loss filtering (ablation)FedRNC · Tiny-ImageNet IID noise (rho=40%)BACC (%): 34.8 -> 40.4Improved
add initial local loss filtering (stage 1) (ablation)FedRNC · Tiny-ImageNet IID noise (rho=40%)BACC (%): 32.6 -> 40.4Improved
add task-wise similarity grouping in prototype matching (ablation)FedRNC · Tiny-ImageNet IID noise (rho=40%)BACC (%): 36.1 -> 40.4Improved
add reuse and relabeling of noisy samples (ablation)FedRNC · Tiny-ImageNet IID noise (rho=40%)BACC (%): 36.8 -> 40.4Improved
relabel noisy samples instead of simply excluding them (ablation)FedRNC · Tiny-ImageNet IID noise (rho=40%)BACC (%): 35.7 -> 40.4Improved
add both FedRNC stages (vs removing prototype matching) to reduce forgetting (ablation)FedRNC · Tiny-ImageNet IID noise (rho=40%)forgetting: 9.2 -> 5.8Improved
plug FedRNC denoising into FL+iCaRLFL+iCaRL · EMNIST (rho=60%)accuracy (%): 40.3 -> 56.3Improved
plug FedRNC denoising into GLFCGLFC · EMNIST (rho=60%)accuracy (%): 53.7 -> 65.8Improved
plug FedRNC denoising into Re-FedRe-Fed · EMNIST (rho=20%)accuracy (%): 65.0 -> 70.9Improved
use FedRNC rather than best baseline at lowest noise on CIFAR-100FedRNC · CIFAR-100 FNCIL IID-noise (rho=20%)accuracy (%): 46.7 -> 45.7Hurt
increase noise rate from 20% to 60% for FedRNC on EMNISTFedRNC · EMNIST FNCIL IID-noiseaccuracy (%): 71.3 -> 71.2No clear effect

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