FedPerGNN

Reported on 5 benchmarks across 1 task

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

Knowledge Base5 results

Recommendation SystemsonMovieLens 100K
RMSE
0.91
Recommendation SystemsonFlixster
RMSE
0.98
best: 0.845 (GRALS)
Recommendation SystemsonMovieLens 1M
RMSE
0.839
best: 0.8227 (GLocal-K)
Recommendation SystemsonMovieLens 10M
RMSE
0.793
best: 0.7485 (Bayesian timeSVD++ flipped)
Recommendation SystemsonDouban
RMSE
0.775
best: 0.6911 (I-CFN)