AI Paper Atlas

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

FedMerge: Federated Model Merging for Personalization

Shutong Chen, Tianyi Zhou, Guodong Long, Jing Jiang, Chengqi Zhang

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Sparse and collaboration-graph personalization · 0 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
use dynamic (learned) merging weights instead of fixed 1/15 (ablation)FedMerge (15 global models) · CIFAR-100 Personal Non-IIDaccuracy: 40.94 -> 51.18Improved
use dynamic merging weights instead of fixed 5/15 (ablation)FedMerge (15 global models) · CIFAR-100 Personal Non-IIDaccuracy: 44.70 -> 51.18Improved
use dynamic merging weights instead of fixed 10/15 (ablation)FedMerge (15 global models) · CIFAR-100 Personal Non-IIDaccuracy: 45.48 -> 51.18Improved
use dynamic merging weights instead of fixed 1/15 (ablation)FedMerge (15 global models) · CIFAR-100 Cluster Non-IIDaccuracy: 32.55 -> 53.27Improved
use dynamic merging weights instead of fixed 5/15 (ablation)FedMerge (15 global models) · CIFAR-100 Cluster Non-IIDaccuracy: 32.52 -> 53.27Improved
use dynamic merging weights instead of fixed 10/15 (ablation)FedMerge (15 global models) · CIFAR-100 Cluster Non-IIDaccuracy: 34.06 -> 53.27Improved
replace FedAvg with FedMerge (15 global models)FedAvg · CIFAR-100 Cluster Non-IIDaccuracy: 30.29 -> 53.27Improved
scale up single-model architecture to larger ResNetssingle-model FL (FedAvg, pFedMoE) · CIFAR-100 Personal/Cluster Non-IIDaccuracyHurt
increase number of ResNet-9 global models for multi-model methodsFedMerge, FedEM, IFCA · CIFAR-100 non-IIDaccuracyImproved
scale up ResNet architecturesingle-model FL · PACS non-IIDaccuracyImproved
replace pFedMoE (two ResNet-18 per client) with FedMerge (one ResNet-9 per client)pFedMoE · CIFAR-100 Personal Non-IIDaccuracy: 54.34 -> 54.38No clear effect
replace FedEM with FedMergeFedEM · Flan federated (average of 8 tasks)ROUGE-1: 73.77 -> 74.86Improved

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