pFedGP-IP-compute

Reported on 6 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology6 results

Federated LearningonCIFAR-10
ACC@1-100Clients· 2021-06-29
88.8
best: 93.25 (SuPerFed-MM)
SOTA
Personalized Federated Learning with Gaussian Processes arXiv:2106.15482
Federated LearningonCIFAR-10
ACC@1-500Clients· 2021-06-29
86.8
best: 90.81 (SuPerFed-MM)
Personalized Federated Learning with Gaussian Processes arXiv:2106.15482
Federated LearningonCIFAR-10
ACC@1-50Clients· 2021-06-29
89.9
best: 94.05 (SuPerFed-MM)
Personalized Federated Learning with Gaussian Processes arXiv:2106.15482
Federated LearningonCIFAR-100
ACC@1-100Clients· 2021-06-29
59.8
best: 61.3 (pFedGP)
Personalized Federated Learning with Gaussian Processes arXiv:2106.15482
Federated LearningonCIFAR-100
ACC@1-500· 2021-06-29
49.2
best: 55.7 (pFedGP-IP-data)
Personalized Federated Learning with Gaussian Processes arXiv:2106.15482
Federated LearningonCIFAR-100
ACC@1-50Clients· 2021-06-29
61.2
best: 63.3 (pFedGP)
Personalized Federated Learning with Gaussian Processes arXiv:2106.15482