Image Classification on CIFAR-10 (test) (Error Bounds and KL Divergence)
0.237Error BoundCNNet9l (baseline)
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| CNNet9l (baseline)Model=CNNet9l, Objective function (Obj.)=f1, beta=250, epsilon=100, rounds="1", Setting=Batch2023.10 | 0.237 | 0.216 | 0.0001 | 0.217 | |
| CNNet9l (baseline)Model=CNNet9l, Objective function (Obj.)=f2, beta=250, epsilon=100, rounds="1", Setting=Batch2023.10 | 0.25 | 0.214 | 0.003 | 0.217 | |
| GenFLModel=CNNet9l, Objective function (Obj.)=f2, beta=5, epsilon=1, rounds=300, KL Penalty=1.0, Number of users=1002023.10 | 0.345 | 0.305 | 0.003 | 0.274 | |
| GenFLModel=CNNet9l, Objective function (Obj.)=f1, beta=5, epsilon=1, rounds=300, KL Penalty=1.0, Number of users=1002023.10 | 0.386 | 0.302 | 0.014 | 0.274 | |
| GenFLModel=CNNet9l, Objective function (Obj.)=f1, beta=5, epsilon=1, rounds=300, KL Penalty=0.1, Number of users=1002023.10 | 0.393 | 0.303 | 0.019 | 0.274 | |
| GenFLModel=CNNet9l, Objective function (Obj.)=f2, beta=5, epsilon=1, rounds=300, KL Penalty=0.1, Number of users=1002023.10 | 0.396 | 0.304 | 0.018 | 0.274 | |
| GenFLModel=CNNet4l, Objective function (Obj.)=f2, beta=10, epsilon=1, rounds=300, KL Penalty=1.0, Number of users=1002023.10 | 0.458 | 0.391 | 0.009 | 0.329 | |
| GenFLModel=CNNet4l, Objective function (Obj.)=f1, beta=10, epsilon=1, rounds=300, KL Penalty=1.0, Number of users=1002023.10 | 0.466 | 0.39 | 0.011 | 0.329 | |
| GenFLModel=CNNet4l, Objective function (Obj.)=f2, beta=10, epsilon=1, rounds=300, KL Penalty=0.1, Number of users=1002023.10 | 0.469 | 0.391 | 0.011 | 0.329 | |
| GenFLModel=CNNet4l, Objective function (Obj.)=f1, beta=10, epsilon=1, rounds=300, KL Penalty=0.1, Number of users=1002023.10 | 0.471 | 0.388 | 0.012 | 0.329 |