AI Paper Atlas

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

Conformal Prediction for Federated Uncertainty Quantification Under Label Shift

Vincent Plassier, Mehdi Makni, Aleksandr Rubashevskii, Eric Moulines, Maxim Panov

ICML 2023 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated 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 label-shift importance weighting to the federated quantile (DP-FedCP) versus unweighted global quantileconformal prediction sets for federated agents · ImageNet label-shift split (11 agents)empirical coverageImproved
Use unweighted global conformal quantile (no label-shift correction)federated conformal prediction · Simulated 2D label-shift experimentempirical coverageHurt
Use only local calibration data (Unweighted Local) for the target agentconformal prediction for small-data agent · Simulated 2D label-shift experimentempirical coverageHurt
Increase Gaussian noise sigma_g from 10 to 100 in DP-FedAvgQE (ablation)DP-FedCP · ImageNetempirical coverage robustnessHurt
Use only local calibration data (Unweighted Local) and global unweighted baselines on CIFAR-10 with label-shifted agentsconformal prediction · CIFAR-10 (10 agents)empirical coverageHurt

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