AI Paper Atlas

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

GeoEvo: Identity-Aware Potential Game with Geometric Evolution for Personalized Multimodal Federated Learning

Chen Wang, Yongli Hu, Huajie Jiang, Kan Guo, Tengfei Liu, Junbin Gao, Yanfeng Sun, Baocai Yin

ICML 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning

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 evolutionary search (NES+PSO) to GeoEvo (ablation)GeoEvo · CREMA-D (50% missing)accuracy (%): 57.6 -> 49.1 without Evo (drop of 8.5 pp)Improved
add geometric coupling (Geo) to GeoEvo (ablation)GeoEvo · CREMA-D (50% missing)accuracy (%): 57.6 -> 50.8 without Geo (drop of 6.8 pp)Improved
add Fisher metric, monotone rule and each evolutionary operator (ablation)GeoEvo · CREMA-D (50% missing)accuracy (%)Improved
add evolutionary search and Frechet prototype coupling to vanilla PMFLPMFL (Vanilla) · CREMA-D (70% missing)accuracy (%): 47.54 -> 54.67Improved
use evolutionary search on top of the prototype-only variantGeoEvo (Prototype) · CREMA-D (50% missing)accuracy (%): 53.90 -> 57.56Improved
replace exact pairwise coupling with single Frechet prototypeOracle (Exact) · CREMA-D (30% missing)accuracy (%): 56.40 -> 56.06No clear effect
replace exact pairwise coupling with single Frechet prototypeOracle (Exact) · CREMA-D (70% missing)accuracy (%): 54.10 -> 54.67Improved
use Fisher-Rao preconditioning instead of diagonal Fisher or Adam-style (ablation)GeoEvo · CREMA-D (local convergence)training loss convergence speedImproved

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