AI Paper Atlas

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

Federated Continuous Category Discovery and Learning

Lixu Wang, Chenxi Liu, Junfeng Guo, Qingqing Ye, Heng Huang, Haibo Hu, Wei Dong

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 1 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 semantic-weighted loss (SWL) aligning samples to global prototypes (ablation)GPA · CIFAR-100 novel accuracynovel accuracy (%): 37.3 -> 52.3Improved
add contrastive weighted loss (CWL) (ablation)GPA · CIFAR-100 novel accuracynovel accuracy (%): 42.9 -> 52.3Improved
add data mixup between confident and residual novel data (ablation)GPA · CIFAR-100 novel accuracynovel accuracy (%): 45.2 -> 52.3Improved
add model mixup instead of distillation (ablation)GPA · CIFAR-100 known accuracyknown accuracy (%): 69.8 -> 71.9Improved
add prototype contrastive loss in known category learning (ablation)GPA · CIFAR-100 novel accuracynovel accuracy (%): 51.1 -> 52.3Improved
use PPM instead of MACC to estimate novel category number (ablation)GPA · CIFAR-100 novel accuracynovel accuracy (%): 39.8 -> 52.3Improved
use PPM instead of MACC or EMaCS for category number estimationnovel category number estimation · 27 category-count settingsaverage error rate (%): 48.9 -> 8.1Improved
apply GPA over Kmeans on FedProx, SCAFFOLD, MoonFL algorithms · FC2DL one-stagenovel accuracyImproved
use GPA instead of best baseline on CUB200 known categoriesFC2DL · CUB200 known accuracyknown accuracy (%): 40.2 -> 40.3No 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