Blind Federated Learning without initial model

Journal of Big Data

Table 3 Blind FL results (constant weights)—Breast Cancer dataset

Agent	Size	% 1s	Accuracy	Accuracy	Precision	Precision
Agent	Size	% 1s	Pre-FL	Post-FL	Pre-FL	Post-FL
1	20%	14%	0.7727	0.9091	0.3750	0.6000
2	20%	26%	0.8696	0.9130	0.7143	0.8333
3	20%	35%	0.6957	0.8261	0.5385	0.7000
4	20%	13%	0.9130	0.9565	0.6667	0.5000
5	20%	26%	0.9565	0.9565	0.8571	0.8571
Avg.	–	–	0.8415	0.9123	0.6303	0.6981
1	19%	24%	0.9091	0.9318	0.8750	0.8889
2	26%	35%	0.8667	0.8833	0.8421	0.8889
3	16%	42%	0.8333	0.8611	1.0000	1.0000
4	15%	20%	0.8824	0.9118	0.6364	0.6364
5	24%	47%	0.8545	0.8727	0.9500	0.9524
Avg.	–	–	0.8692	0.8922	0.8607	0.8733
1	5%	27%	0.7500	0.7500	0.5000	0.5000
2	4%	43%	0.8000	0.8000	1.000	1.0000
3	42%	35%	0.9167	0.9271	0.9063	0.8824
4	20%	23%	0.9778	0.9778	0.9091	0.9091
5	29%	49%	0.7727	0.7727	0.9500	0.9048
Avg.	–	–	0.8434	0.8455	0.8531	0.8392
1	3%	20%	1.0000	1.0000	1.0000	0.5000
2	4%	36%	0.8000	0.8000	1.0000	1.0000
3	45%	40%	0.9327	0.9423	0.9268	0.9474
4	21%	17%	0.8542	0.8958	0.5454	0.6364
5	26%	49%	0.8361	0.8689	0.8889	0.9583
Avg.	–	–	0.8846	0.9014	0.8722	0.8084