AI Paper Atlas

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

Local and Global Flatness for Federated Domain Generalization

Hao Yan, Yuhong Guo

ECCV 2024 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated learning with pretrained models · 3 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 local flatness regularization (adversarial KL divergence) to ERM (ablation)FedAvg with additive perturbation · PACS partialaverage accuracy (%): 68.8 -> 73.6Improved
add global flatness regularization to ERM (ablation)FedAvg with additive perturbation · PACS partialaverage accuracy (%): 68.8 -> 75.1Improved
combine local and global flatness losses (ablation)FedAvg with additive perturbation · PACS partialaverage accuracy (%): 75.1 -> 77.9Improved
combine local and global flatness losses (ablation)FedAvg with singular perturbation · PACS partialaverage accuracy (%): 78.0 -> 79.3Improved
use singular instead of additive perturbation (ablation)FedLGF · Federated DG partial scenario (avg)test accuracy (%): 78.0 -> 78.4Improved
use singular instead of additive perturbation (ablation)FedLGF · Federated DG full scenario (avg)test accuracy (%): 81.9 -> 81.6Hurt
apply weight perturbation to feature encoder conv layers as well as classifier (ablation)FedLGF · federated DG benchmarksaccuracyHurt
add FedLGF to FedAvg in partial scenarioFedAvg · Federated DG partial (avg)test accuracy (%): 71.3 -> 78.4Improved
vary trade-off hyperparameters below 1 (ablation)FedLGF · PACS partialaverage accuracyNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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