Table 2:

Performance of Several models trained using classical machine learning methods, and federated learning methods, where the number of participating clients in the federation is $N=2$, tested on the PDBP dataset. Data reported is mean and standard deviation across K=6 fold cross validation.

Algorithm Name	ROC-AUC	AUC-PR	Balanced Accuracy	Precision	Recall	F 0.5	F 1	F 2	Log Loss	Matthews Correlation Coefficient
AdaBoost Classifier	0.834±0.021	0.891±0.015	0.697±0.026	0.757±0.023	0.917±0.033	0.835±0.016	0.834±0.009	0.905±0.004	0.639±0.005	0.456±0.029
Bagging	0.812±0.01	0.871±0.01	0.696±0.019	0.753±0.015	0.932±0.015	0.828±0.007	0.84±0.004	0.903±0.003	1.291±0.226	0.463±0.027
GradientBoosting Classifier	0.856±0.013	0.9±0.016	0.716±0.018	0.766±0.014	0.938±0.013	0.856±0.007	0.857±0.003	0.908±0.003	0.572±0.042	0.502±0.024
KNeighbors Classifier	0.586±0.024	0.735±0.019	0.551±0.019	0.664±0.011	0.946±0.024	0.707±0.008	0.783±0.001	0.899±0.0	3.322±0.641	0.169±0.042
LinearDiscriminantAnalysis Classifier	0.702±0.012	0.794±0.008	0.64±0.013	0.734±0.01	0.776±0.01	0.622±0.305	0.661±0.324	0.751±0.368	2.104±0.19	0.288±0.024
LogisticRegression Classifier	0.771±0.011	0.842±0.009	0.657±0.008	0.73±0.005	0.901±0.01	0.791±0.004	0.81±0.005	0.901±0.001	0.996±0.039	0.368±0.02
MLP Classifier	0.671±0.013	0.826±0.007	0.619±0.012	0.711±0.008	0.839±0.01	0.749±0.009	0.789±0.007	0.899±0.001	8.313±0.708	0.265±0.026
QuadraticDiscriminantAnalysis Classifier	0.525±0.022	0.721±0.022	0.525±0.022	0.671±0.024	0.366±0.097	0.688±0.0	0.779±0.0	0.898±0.0	18.716±1.33	0.05±0.042
RandomForest	0.736±0.006	0.825±0.005	0.524±0.005	0.649±0.003	0.985±0.005	0.764±0.007	0.792±0.005	0.899±0.0	0.596±0.004	0.132±0.025
SGD Classifier	0.662±0.017	0.845±0.007	0.65±0.016	0.728±0.011	0.878±0.024	0.758±0.01	0.803±0.007	0.898±0.0	10.11±0.525	0.343±0.034
SVC Classifier	0.701±0.007	0.808±0.004	0.593±0.011	0.693±0.006	0.844±0.02	0.742±0.004	0.793±0.002	0.901±0.001	0.65±0.019	0.214±0.029
XGBoost Classifier	0.862±0.008	0.905±0.007	0.719±0.021	0.77±0.016	0.932±0.013	0.864±0.006	0.857±0.003	0.906±0.003	0.691±0.031	0.504±0.03
XGBoost Random Forest Classifier	0.829±0.007	0.89±0.006	0.732±0.02	0.781±0.016	0.918±0.01	0.849±0.003	0.855±0.002	0.905±0.003	2.715±0.254	0.515±0.031
FedAvg LR	0.665±0.128	0.826±0.011	0.565±0.052	0.673±0.028	0.96±0.032	0.745±0.045	0.794±0.012	0.899±0.002	0.829±0.108	0.187±0.147
FedAvg MLP	0.69±0.018	0.78±0.012	0.629±0.01	0.719±0.007	0.828±0.022	0.744±0.008	0.791±0.007	0.899±0.001	1.038±0.239	0.282±0.024
FedAvg SGD	0.775±0.011	0.847±0.008	0.689±0.011	0.77±0.008	0.8±0.01	0.794±0.005	0.809±0.004	0.902±0.002	0.559±0.013	0.385±0.023
FedAvg XGBRF	0.794±0.007	0.876±0.009	0.695±0.023	0.754±0.017	0.919±0.012	0.825±0.007	0.838±0.008	0.902±0.003	0.691±0.0	0.451±0.035
FedProx μ = 0.5 LR	0.704±0.101	0.823±0.015	0.584±0.042	0.683±0.022	0.943±0.03	0.762±0.038	0.795±0.009	0.9±0.002	0.866±0.092	0.232±0.115
FedProx μ = 0.5 MLP	0.7±0.008	0.791±0.006	0.63±0.011	0.719±0.007	0.833±0.016	0.748±0.007	0.794±0.004	0.899±0.001	1.312±0.124	0.284±0.023
FedProx μ = 2 LR	0.761±0.008	0.835±0.007	0.601±0.005	0.691±0.003	0.947±0.013	0.787±0.008	0.804±0.003	0.9±0.001	0.875±0.014	0.293±0.01
FedProx μ = 2 MLP	0.695±0.022	0.785±0.015	0.631±0.02	0.722±0.013	0.818±0.02	0.747±0.014	0.791±0.005	0.899±0.001	1.231±0.285	0.282±0.044