AI Paper Atlas

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

Federated Representation Angle Learning

Liping Yi, Han Yu, Gang Wang, Xiaoguang Liu, Xiaoxiao Li

ICCV 2025 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated 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 adaptive diagonal sparsification (ablation)FedRAL · CIFAR-10 (pathological)average accuracy (%): 91.64 -> 93.60Improved
add adaptive diagonal sparsification (ablation)FedRAL · CIFAR-100 (pathological)average accuracy (%): 56.58 -> 58.70Improved
add adaptive diagonal sparsification (ablation)FedRAL · CIFAR-10 (practical)average accuracy (%): 41.37 -> 42.97Improved
add adaptive diagonal sparsification (ablation)FedRAL · CIFAR-100 (practical)average accuracy (%): 11.58 -> 11.70No clear effect
use ordinate-wise weighted aggregation instead of naive averaging (ablation)FedRAL · CIFAR-10 (pathological)average accuracy (%): 93.47 -> 93.60No clear effect
use ordinate-wise weighted aggregation instead of naive averaging (ablation)FedRAL · CIFAR-100 (pathological)average accuracy (%): 53.94 -> 58.70Improved
use ordinate-wise weighted aggregation instead of naive averaging (ablation)FedRAL · CIFAR-10 (practical)average accuracy (%): 40.52 -> 42.97Improved
use ordinate-wise weighted aggregation instead of naive averaging (ablation)FedRAL · CIFAR-100 (practical)average accuracy (%): 9.24 -> 11.70Improved
use FedRAL instead of FedTGPFedRAL · CIFAR-100 (practical non-IID)average test accuracy (%): 9.37 -> 11.70Improved
use FedRAL instead of FedTGPFedRAL · CIFAR-100 (pathological non-IID)average test accuracy (%): 53.20 -> 58.70Improved
use FedRAL instead of FedTGPFedRAL · CIFAR-100 (communication rounds)rounds to target accuracy: 354 -> 144Improved
use FedRAL instead of FedTGP under high model heterogeneityFedRAL · CIFAR-100 (100 clients)average accuracy (%): 48.69 -> 50.79Improved

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