AI Paper Atlas

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

Deep Neural Network Fusion via Graph Matching with Applications to Model Ensemble and Federated Learning

Chang Liu, Chenfei Lou, Runzhong Wang, Alan Yuhan Xi, Li Shen, Junchi Yan

ICML 2022 · 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
Use GAMF (second-order graph matching fusion) instead of OTFusion (first-order linear assignment) for one-shot fusionLeNet fusion, 2 models · CIFAR-10 homogeneous one-shotaccuracy (%): 49.79 vs 39.04Improved
Use GAMF instead of OTFusion for fusion followed by finetuningVGG11 fusion, 2 models, heterogeneous · CIFAR-10 finetuneaccuracy (%): 79.40 vs 62.08Improved
Use GAMF instead of OTFusion in the 4-model homogeneous VGG11 one-shot settingVGG11 fusion, 4 models · CIFAR-10 homogeneous one-shotaccuracy (%): 73.42 vs 73.56Hurt
Use GAMF instead of OTFusion for federated learningVGG11 federated learning · CIFAR-100 5 clientstop-1 accuracy (%): 49.80 vs 1.00 (OTFusion fails to converge)Improved
Combine GAMF with Moon local contrastive training (ablation)federated learning, VGG11 · CIFAR-10 10 clientstop-1 accuracy (%): 73.43 vs 72.39 (GAMF) and 72.42 (Moon)Improved
Use GAMF instead of FedAvg-style parameter averaging in federated learningVGG11 federated learning · CIFAR-10 20 clientstop-1 accuracy (%): 71.37 vs 65.70Improved
Use second-order similarity (GAMF) instead of first-order similarity (OTFusion) for channel alignment (ablation)VGG11 compact ensemble · CIFAR-10 similarity-accuracy scatteraccuracy (%)Improved
Use GAMF instead of OTFusion on MNIST heterogeneous ensembleConvnet fusion · MNIST heterogeneous ensembleaccuracy (%)Improved

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