Blind Federated Learning without initial model

Journal of Big Data

Table 5 Blended 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%	0.6818	0.9091	0.3000	0.6000
2	20%	26%	0.9130	0.9130	0.8333	0.8333
3	20%	35%	0.8696	0.8696	0.7778	0.7778
4	20%	13%	0.9130	0.9565	0.6667	0.5000
5	20%	26%	0.9565	1.0000	0.8571	1.0000
Avg.	–	–	0.8668	0.9296	0.6870	0.7422
1	19%	24%	0.9091	0.9318	0.8750	0.8889
2	26%	35%	0.8667	0.9000	0.8421	0.8889
3	16%	42%	0.8611	0.8611	1.0000	1.0000
4	15%	20%	0.8824	0.8824	0.6364	0.6364
5	24%	47%	0.8364	0.8728	0.9474	0.9524
Avg.	–	–	0.8711	0.8896	0.8602	0.8733
1	5%	27%	0.6667	0.7500	0.4000	0.5000
2	4%	43%	0.7000	0.7000	1.0000	1.0000
3	42%	35%	0.9479	0.9479	0.9394	0.8824
4	20%	23%	0.9778	0.9778	0.9091	0.9091
5	29%	49%	0.7576	0.7576	0.9048	0.9048
Avg.	–	–	0.8100	0.8267	0.8306	0.8392
1	3%	20%	0.8333	0.8333	0.5000	0.5000
2	4%	36%	0.8000	0.8000	1.0000	1.0000
3	45%	40%	0.9519	0.9519	0.9744	0.9500
4	21%	17%	0.8750	0.8958	0.5833	0.6364
5	26%	49%	0.8033	0.8689	0.9130	0.9583
Avg.	–	–	0.8527	0.8700	0.7941	0.8089