import csv
from utils.sampling import mnist_iid, mnist_noniid, cifar_iid
from utils.options import args_parser
from models.CIFAR_Updates_v2_labelFlipping import LocalUpdate
from models.Nets import MLP, CNNMnist, CNNCifar, customCNNCifar
from models.Fed import FedAvg
#from models.test import test_img
from models.CIFAR_test_v2_labelFlipping import test_img
from collections import OrderedDict,defaultdict
if __name__ == '__main__':
start = time.time()
# parse args
args = args_parser()
args.device = torch.device('cuda:{}'.format(args.gpu) if torch.cuda.is_available() and args.gpu != -1 else 'cpu')
# load dataset and split users
if args.dataset == 'mnist':
trans_mnist = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
dataset_train = datasets.MNIST('data/mnist/', train=True, download=True, transform=trans_mnist)
dataset_test = datasets.MNIST('data/mnist/', train=False, download=True, transform=trans_mnist)
# sample users
if args.iid:
dict_users = mnist_iid(dataset_train, args.num_users)
else:
dict_users = mnist_noniid(dataset_train, args.num_users)
elif args.dataset == 'cifar':
trans_cifar_train = transforms.Compose([transforms.RandomCrop(32,padding=4),transforms.RandomHorizontalFlip(),transforms.ToTensor(), transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])
trans_cifar_test = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010))])
def main():
# parse args
args = args_parser()
args.device = torch.device('cuda:{}'.format(
args.gpu) if torch.cuda.is_available() and args.gpu != -1 else 'cpu')
# load dataset and split users
if args.dataset == 'mnist':
trans_mnist = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
])
dataset_train = datasets.MNIST('../data/mnist/',
train=True,
download=True,
transform=trans_mnist)
dataset_test = datasets.MNIST('../data/mnist/',
train=False,
download=True,
transform=trans_mnist)
print("type of test dataset", type(dataset_test))
# sample users
if args.iid:
dict_users = mnist_iid(dataset_train, args.num_users)
else:
dict_users, dict_labels_counter = mnist_noniid(
dataset_train, args.num_users)
dict_users_2, dict_labels_counter_2 = dict_users, dict_labels_counter
#dict_users, dict_labels_counter = mnist_noniid_unequal(dataset_train, args.num_users)
elif args.dataset == 'cifar':
trans_cifar = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
dataset_train = datasets.CIFAR10('../data/cifar',
train=True,
download=True,
transform=trans_cifar)
dataset_test = datasets.CIFAR10('../data/cifar',
train=False,
download=True,
transform=trans_cifar)
if args.iid:
dict_users = cifar_iid(dataset_train, args.num_users)
else:
exit('Error: only consider IID setting in CIFAR10')
else:
exit('Error: unrecognized dataset')
img_size = dataset_train[0][0].shape
# build model
if args.model == 'cnn' and args.dataset == 'cifar':
net_glob = CNNCifar(args=args).to(args.device)
net_glob_2 = CNNCifar(args=args).to(args.device)
elif args.model == 'cnn' and args.dataset == 'mnist':
net_glob = CNNMnist(args=args).to(args.device)
net_glob_2 = CNNMnist(args=args).to(args.device)
elif args.model == 'mlp':
len_in = 1
for x in img_size:
len_in *= x
net_glob = MLP(dim_in=len_in, dim_hidden=200,
dim_out=args.num_classes).to(args.device)
else:
exit('Error: unrecognized model')
#print(net_glob)
#net_glob.train()
acc_test, loss_test = test_img(net_glob, dataset_test, args)
print("val test finished")
print("{:.2f}".format(acc_test))
temp = net_glob
#net_glob_2 = net_glob
temp_2 = net_glob_2
# copy weights
w_glob = net_glob.state_dict()
# training
loss_train = []
cv_loss, cv_acc = [], []
val_loss_pre, counter = 0, 0
net_best = None
best_loss = None
val_acc_list, net_list = [], []
Loss_local_each_global_total = []
test_ds, valid_ds = torch.utils.data.random_split(dataset_test,
(9500, 500))
loss_workers_total = np.zeros(shape=(args.num_users, args.epochs))
label_workers = {
i: np.array([], dtype='int64')
for i in range(args.num_users)
}
workers_percent = []
workers_count = 0
acc_test_global, loss_test_global = test_img(x, valid_ds, args)
selected_users_index = []
for idx in range(args.num_users):
# print("train started")
local = LocalUpdate(args=args,
dataset=dataset_train,
idxs=dict_users[idx])
w, loss = local.train(net=copy.deepcopy(net_glob).to(args.device))
# print(w)
# print("train completed")
# temp = FedAvg(w)
temp.load_state_dict(w)
temp.eval()
acc_test_local, loss_test_local = test_img(temp, valid_ds, args)
loss_workers_total[idx, iter] = acc_test_local
if workers_count >= (args.num_users / 2):
break
elif acc_test_local >= (0.7 * acc_test_global):
selected_users_index.append(idx)
for iter in range(args.epochs):
print("round started")
Loss_local_each_global = []
loss_workers = np.zeros((args.num_users, args.epochs))
w_locals, loss_locals = [], []
m = max(int(args.frac * args.num_users), 1)
#idxs_users = np.random.choice(range(args.num_users), m, replace=False)
#if iter % 5 == 0:
# Minoo
x = net_glob
x.eval()
Loss_local_each_global_total.append(acc_test_global)
for idx in selected_users_index:
#print("train started")
local = LocalUpdate(args=args,
dataset=dataset_train,
idxs=dict_users[idx])
w, loss = local.train(net=copy.deepcopy(net_glob).to(args.device))
#print(w)
#print("train completed")
#temp = FedAvg(w)
temp.load_state_dict(w)
temp.eval()
acc_test_local, loss_test_local = test_img(temp, valid_ds, args)
loss_workers_total[idx, iter] = acc_test_local
if workers_count >= (args.num_users / 2):
break
elif acc_test_local >= (0.7 * acc_test_global):
w_locals.append(copy.deepcopy(w))
loss_locals.append(copy.deepcopy(loss))
print("Update Received")
workers_count += 1
# update global weights
w_glob = FedAvg(w_locals)
# copy weight to net_glob
net_glob.load_state_dict(w_glob)
print("round completed")
loss_avg = sum(loss_locals) / len(loss_locals)
print('Round {:3d}, Average loss {:.3f}'.format(iter, loss_avg))
loss_train.append(loss_avg)
workers_percent.append(workers_count)
# plot loss curve
plt.figure()
plt.plot(range(len(workers_percent)), workers_percent)
plt.ylabel('train_loss')
plt.savefig(
'./save/Newfed_WorkersPercent_0916_{}_{}_{}_C{}_iid{}.png'.format(
args.dataset, args.model, args.epochs, args.frac, args.iid))
# print(loss_workers_total)
# plot loss curve
# plt.figure()
# plt.plot(range(len(loss_train)), loss_train)
# plt.ylabel('train_loss')
# plt.savefig('./save/Newfed_0916_{}_{}_{}_C{}_iid{}.png'.format(args.dataset, args.model, args.epochs, args.frac, args.iid))
#
plt.figure()
for i in range(args.num_users):
plot = plt.plot(range(len(loss_workers_total[i, :])),
loss_workers_total[i, :],
label="Worker {}".format(i))
plot5 = plt.plot(range(len(Loss_local_each_global_total)),
Loss_local_each_global_total,
color='000000',
label="Global")
plt.legend(loc='best')
plt.ylabel('Small Test Set Accuracy of workers')
plt.xlabel('Number of Rounds')
plt.savefig(
'./save/NewFed_2workers_Acc_0916_{}_{}_{}_C{}_iid{}.png'.format(
args.dataset, args.model, args.epochs, args.frac, args.iid))
# plt.figure()
# bins = np.linspace(0, 9, 3)
# a = dict_labels_counter[:, 0].ravel()
# print(type(a))
# b = dict_labels_counter[:, 1].ravel()
# x_labels = ['0', '1', '2', '3','4','5','6','7','8','9']
# # Set plot parameters
# fig, ax = plt.subplots()
# width = 0.1 # width of bar
# x = np.arange(10)
# ax.bar(x, dict_labels_counter[:, 0], width, color='#000080', label='Worker 1')
# ax.bar(x + width, dict_labels_counter[:, 1], width, color='#73C2FB', label='Worker 2')
# ax.bar(x + 2*width, dict_labels_counter[:, 2], width, color='#ff0000', label='Worker 3')
# ax.bar(x + 3*width, dict_labels_counter[:, 3], width, color='#32CD32', label='Worker 4')
# ax.set_ylabel('Number of Labels')
# ax.set_xticks(x + width + width / 2)
# ax.set_xticklabels(x_labels)
# ax.set_xlabel('Labels')
# ax.legend()
# plt.grid(True, 'major', 'y', ls='--', lw=.5, c='k', alpha=.3)
# fig.tight_layout()
# plt.savefig(
# './save/Newfed_2workersLabels_0916_{}_{}_{}_C{}_iid{}.png'.format(args.dataset, args.model, args.epochs, args.frac,
# args.iid))
# testing
print("testing started")
net_glob.eval()
print("train test started")
acc_train_final, loss_train_final = test_img(net_glob, dataset_train, args)
print("train test finished")
acc_test_final, loss_test_final = test_img(net_glob, dataset_test, args)
print("val test finished")
#print("Training accuracy: {:.2f}".format(acc_train))
#print("Testing accuracy: {:.2f}".format(acc_test))
print("{:.2f}".format(acc_test_final))
#print("{:.2f".format(Loss_local_each_worker))
# training
w_glob_2 = net_glob_2.state_dict()
loss_train_2 = []
cv_loss_2, cv_acc_2 = [], []
val_loss_pre_2, counter_2 = 0, 0
net_best_2 = None
best_loss_2 = None
val_acc_list_2, net_list_2 = [], []
Loss_local_each_global_total_2 = []
loss_workers_total_2 = np.zeros(shape=(args.num_users, args.epochs))
label_workers_2 = {
i: np.array([], dtype='int64')
for i in range(args.num_users)
}
for iter in range(args.epochs):
print("round started")
Loss_local_each_global_2 = []
loss_workers_2 = np.zeros((args.num_users, args.epochs))
w_locals_2, loss_locals_2 = [], []
m_2 = max(int(args.frac * args.num_users), 1)
idxs_users_2 = np.random.choice(range(args.num_users),
m_2,
replace=False)
# Minoo
x_2 = net_glob_2
x_2.eval()
acc_test_global_2, loss_test_global_2 = test_img(x_2, valid_ds, args)
Loss_local_each_global_total_2.append(acc_test_global_2)
for idx in idxs_users_2:
#print("train started")
local_2 = LocalUpdate(args=args,
dataset=dataset_train,
idxs=dict_users_2[idx])
w_2, loss_2 = local_2.train(
net=copy.deepcopy(net_glob_2).to(args.device))
#print(w)
#print("train completed")
w_locals_2.append(copy.deepcopy(w_2))
loss_locals_2.append(copy.deepcopy(loss_2))
#temp = FedAvg(w)
temp_2.load_state_dict(w_2)
temp_2.eval()
acc_test_local_2, loss_test_local_2 = test_img(
temp_2, valid_ds, args)
loss_workers_total_2[idx, iter] = acc_test_local_2
# update global weights
w_glob_2 = FedAvg(w_locals_2)
# copy weight to net_glob
net_glob_2.load_state_dict(w_glob_2)
print("round completed")
loss_avg_2 = sum(loss_locals_2) / len(loss_locals_2)
print('Round {:3d}, Average loss {:.3f}'.format(iter, loss_avg_2))
loss_train_2.append(loss_avg_2)
print("round completed")
# plot loss curve
plt.figure()
plt.plot(range(len(loss_train_2)),
loss_train_2,
color='#000000',
label="Main FL")
plt.plot(range(len(loss_train)),
loss_train,
color='#ff0000',
label="Centralized Algorithm")
plt.ylabel('train_loss')
plt.savefig('./save/main_fed_0916_{}_{}_{}_C{}_iid{}.png'.format(
args.dataset, args.model, args.epochs, args.frac, args.iid))
# print(loss_workers_total)
plt.figure()
for i in range(args.num_users):
plot = plt.plot(range(len(loss_workers_total_2[i, :])),
loss_workers_total_2[i, :],
label="Worker {}".format(i))
plot5 = plt.plot(range(len(Loss_local_each_global_total_2)),
Loss_local_each_global_total_2,
color='000000',
label="Global")
plt.legend(loc='best')
plt.ylabel('Small Test Set Accuracy of workers')
plt.xlabel('Number of Rounds')
plt.savefig('./save/mainfed_Acc_0916_{}_{}_{}_C{}_iid{}.png'.format(
args.dataset, args.model, args.epochs, args.frac, args.iid))
# plt.figure()
# bins = np.linspace(0, 9, 3)
# a = dict_labels_counter_2[:, 0].ravel()
# print(type(a))
# b = dict_labels_counter_2[:, 1].ravel()
# x_labels = ['0', '1', '2', '3','4','5','6','7','8','9']
# # Set plot parameters
# fig, ax = plt.subplots()
# width = 0.1 # width of bar
# x = np.arange(10)
# ax.bar(x, dict_labels_counter_2[:, 0], width, color='#000080', label='Worker 1')
# ax.bar(x + width, dict_labels_counter_2[:, 1], width, color='#73C2FB', label='Worker 2')
# ax.bar(x + 2*width, dict_labels_counter_2[:, 2], width, color='#ff0000', label='Worker 3')
# ax.bar(x + 3*width, dict_labels_counter_2[:, 3], width, color='#32CD32', label='Worker 4')
# ax.set_ylabel('Number of Labels')
# ax.set_xticks(x + width + width / 2)
# ax.set_xticklabels(x_labels)
# ax.set_xlabel('Labels')
# ax.legend()
# plt.grid(True, 'major', 'y', ls='--', lw=.5, c='k', alpha=.3)
# fig.tight_layout()
# plt.savefig(
# './save/main_fed_2workersLabels_0916_{}_{}_{}_C{}_iid{}.png'.format(args.dataset, args.model, args.epochs, args.frac,
# args.iid))
# testing
print("testing started")
net_glob.eval()
print("train test started")
acc_train_final, loss_train_final = test_img(net_glob, dataset_train, args)
print("train test finished")
acc_test_final, loss_test_final = test_img(net_glob, dataset_test, args)
print("val test finished")
#print("Training accuracy: {:.2f}".format(acc_train))
#print("Testing accuracy: {:.2f}".format(acc_test))
print("{:.2f}".format(acc_test_final))
#print("{:.2f".format(Loss_local_each_worker))
return loss_test_final, loss_train_final
import copy
import numpy as np
from torchvision import datasets, transforms # torchvision是pytorch的一个图形库，它服务于PyTorch深度学习框架的，主要用来构建计算机视觉模型；transforms主要是用于常见的一些图形变换
import torch
from utils.sampling import mnist_iid, mnist_noniid, cifar_iid
from utils.options import args_parser
from models.Update import LocalUpdate
from models.Nets import MLP, CNNMnist, CNNCifar
from models.Fed import FedAvg
from models.test import test_img
if __name__ == '__main__':
# parse args
args = args_parser() #读取设置好的参数
args.device = torch.device('cuda:{}'.format(
args.gpu) if torch.cuda.is_available() and args.gpu != -1 else 'cpu')
# load dataset and split users
if args.dataset == 'mnist':
trans_mnist = transforms.Compose(
[
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
]
) # ToTensor()的变换操作是关键一步，它将PILImage转变为torch.FloatTensor的数据形式，这种数据形式一定是C x H x W的图像格式加上[0,1]的大小范围。它将颜色通道这一维从第三维变换到了第一维；最后的Normalize变换是对tensor这种数据格式进行的，它的操作是用给定的均值和标准差分别对每个通道的数据进行正则化。因为mnist数据值都是灰度图，所以图像的通道数n=1；mnist手写体数据集里的标准化参数
dataset_train = datasets.MNIST('../data/mnist/',
train=True,
download=True,
transform=trans_mnist)
def main():
manualSeed = 1
np.random.seed(manualSeed)
random.seed(manualSeed)
torch.manual_seed(manualSeed)
# if you are suing GPU
torch.cuda.manual_seed(manualSeed)
torch.cuda.manual_seed_all(manualSeed)
torch.backends.cudnn.enabled = False
torch.backends.cudnn.benchmark = False
torch.backends.cudnn.deterministic = True
# parse args
args = args_parser()
args.device = torch.device('cuda:{}'.format(
args.gpu) if torch.cuda.is_available() and args.gpu != -1 else 'cpu')
# load dataset and split users
if args.dataset == 'mnist':
trans_mnist = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
])
dataset_train = datasets.MNIST('../data/mnist/',
train=True,
download=True,
transform=trans_mnist)
dataset_test = datasets.MNIST('../data/mnist/',
train=False,
download=True,
transform=trans_mnist)
# sample users
if args.iid:
dict_users_DCFL = mnist_iid(dataset_train, args.num_users)
else:
dict_users_DCFL, dict_labels_counter = mnist_noniid(
dataset_train, args.num_users)
dict_users_mainFL, dict_labels_counter_mainFL = dict_users_DCFL, dict_labels_counter
elif args.dataset == 'cifar':
trans_cifar = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
dataset_train = datasets.CIFAR10('../data/cifar',
train=True,
download=True,
transform=trans_cifar)
dataset_test = datasets.CIFAR10('../data/cifar',
train=False,
download=True,
transform=trans_cifar)
if args.iid:
dict_users_DCFL = cifar_iid(dataset_train, args.num_users)
dict_users_mainFL = dict_users_DCFL
dict_labels_counter_mainFL = dict()
dict_labels_counter = dict()
else:
dict_users_DCFL, dict_labels_counter = cifar_noniid(
dataset_train, args.num_users)
dict_users_mainFL, dict_labels_counter_mainFL = dict_users_DCFL, dict_labels_counter
elif args.dataset == 'fmnist':
trans_fmnist = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
])
dataset_train = datasets.FashionMNIST('../data/fmnist',
train=True,
download=True,
transform=trans_fmnist)
dataset_test = datasets.FashionMNIST('../data/fmnist',
train=False,
download=True,
transform=trans_fmnist)
if args.iid:
print("iid")
dict_users_DCFL = mnist_iid(dataset_train, args.num_users)
else:
print("non iid")
dict_users_DCFL, dict_labels_counter = mnist_noniid(
dataset_train, args.num_users)
dict_users_mainFL, dict_labels_counter_mainFL = dict_users_DCFL, dict_labels_counter
else:
exit('Error: unrecognized dataset')
img_size = dataset_train[0][0].shape
# Small shared dataset
test_ds, valid_ds_before = torch.utils.data.random_split(
dataset_test, (9500, 500))
small_shared_dataset = create_shared_dataset(valid_ds_before, 200)
optimal_delay = 1.0
# Start process for each fraction of c
for c_counter in range(3, 3 + 1, 2):
if args.model == 'cnn' and args.dataset == 'cifar':
net_glob = CNNCifar(args=args).to(args.device)
# net_glob_mainFL = copy.deepcopy(net_glob)
elif args.model == 'cnn' and args.dataset == 'mnist':
net_glob = CNNMnist(args=args).to(args.device)
# net_glob_mainFL = copy.deepcopy(net_glob)
elif args.model == 'cnn' and args.dataset == 'fmnist':
net_glob = CNNFashion_Mnist(args=args).to(args.device)
# net_glob_mainFL = copy.deepcopy(net_glob)
elif args.model == 'mlp':
len_in = 1
for x in img_size:
len_in *= x
net_glob = MLP(dim_in=len_in,
dim_hidden=200,
dim_out=args.num_classes).to(args.device)
else:
exit('Error: unrecognized model')
# Saving data
data_Global_main = {
"C": [],
"Round": [],
"Average Loss Train": [],
"SDS Loss": [],
"SDS Accuracy": [],
"Workers Number": [],
"Large Test Loss": [],
"Large Test Accuracy": [],
"Communication Cost": []
}
Final_LargeDataSetTest_MainFL = {
"C": [],
"Test Accuracy": [],
"Test Loss": [],
"Train Loss": [],
"Train Accuracy": [],
"Total Rounds": [],
"Communication Cost": []
}
data_Global_DCFL = {
"C": [],
"Round": [],
"Average Loss Train": [],
"SDS Loss": [],
"SDS Accuracy": [],
"Workers Number": [],
"Large Test Loss": [],
"Large Test Accuracy": [],
"Communication Cost": []
}
Final_LargeDataSetTest_DCFL = {
"C": [],
"Test Accuracy": [],
"Test Loss": [],
"Train Loss": [],
"Train Accuracy": [],
"Total Rounds": [],
"Communication Cost": []
}
data_Global_G1 = {
"C": [],
"Round": [],
"Average Loss Train": [],
"SDS Loss": [],
"SDS Accuracy": [],
"Workers Number": [],
"Large Test Loss": [],
"Large Test Accuracy": [],
"Communication Cost": []
}
Final_LargeDataSetTest_G1 = {
"C": [],
"Test Accuracy": [],
"Test Loss": [],
"Train Loss": [],
"Train Accuracy": [],
"Total Rounds": [],
"Communication Cost": []
}
data_Global_G2 = {
"C": [],
"Round": [],
"Average Loss Train": [],
"SDS Loss": [],
"SDS Accuracy": [],
"Workers Number": [],
"Large Test Loss": [],
"Large Test Accuracy": [],
"Communication Cost": []
}
Final_LargeDataSetTest_G2 = {
"C": [],
"Test Accuracy": [],
"Test Loss": [],
"Train Loss": [],
"Train Accuracy": [],
"Total Rounds": [],
"Communication Cost": []
}
data_Global_Muhammed = {
"C": [],
"Round": [],
"Average Loss Train": [],
"SDS Loss": [],
"SDS Accuracy": [],
"Workers Number": [],
"Large Test Loss": [],
"Large Test Accuracy": [],
"Communication Cost": []
}
Final_LargeDataSetTest_Muhammed = {
"C": [],
"Test Accuracy": [],
"Test Loss": [],
"Train Loss": [],
"Train Accuracy": [],
"Total Rounds": [],
"Communication Cost": []
}
data_Global_Cho = {
"C": [],
"Round": [],
"Average Loss Train": [],
"SDS Loss": [],
"SDS Accuracy": [],
"Workers Number": [],
"Large Test Loss": [],
"Large Test Accuracy": [],
"Communication Cost": []
}
Final_LargeDataSetTest_Cho = {
"C": [],
"Test Accuracy": [],
"Test Loss": [],
"Train Loss": [],
"Train Accuracy": [],
"Total Rounds": [],
"Communication Cost": []
}
net_glob.train()
net_glob_mainFL = copy.deepcopy(net_glob)
net_glob_G1 = copy.deepcopy(net_glob)
net_glob_G2 = copy.deepcopy(net_glob)
cost = np.random.rand(args.num_users)
R_G1 = 5
args.frac = (c_counter / 10)
# Main FL
loss_main, dict_workers_index, Final_LargeDataSetTest_MainFL_temp, data_Global_main_temp = mainFl(
net_glob_mainFL, dict_users_mainFL, dict_labels_counter_mainFL,
args, cost, dataset_train, dataset_test, small_shared_dataset)
Final_LargeDataSetTest_MainFL = merge(
Final_LargeDataSetTest_MainFL, Final_LargeDataSetTest_MainFL_temp)
data_Global_main = merge(data_Global_main, data_Global_main_temp)
# with open(os.path.join(OUT_DIR, f"dict_users_mainFL-C-{args.frac}-{args.dataset}.pkl"), 'wb') as file:
# pickle.dump(dict_users_mainFL, file)
# with open(os.path.join(OUT_DIR, f"dict_users_mainFL-C-{args.frac}-{args.dataset}.pkl"), 'rb') as file:
# dict_users_mainFL = pickle.load(file)
# with open(os.path.join(OUT_DIR, f"workers_index-C-{args.frac}-{args.dataset}.pkl"), 'wb') as file:
# pickle.dump(dict_workers_index, file)
# with open(os.path.join(OUT_DIR, f"cost-C-{args.frac}-{args.dataset}.pkl"), 'wb') as file:
# pickle.dump(cost, file)
# with open(os.path.join(OUT_DIR, f"cost-C-{args.frac}-{args.dataset}.pkl"), 'rb') as file:
# cost = pickle.load(file)
# print(cost)
# with open(os.path.join(OUT_DIR, f"GoalLoss-C-{args.frac}-{args.dataset}.pkl"), 'wb') as file:
# pickle.dump(loss_main, file)
date = datetime.now()
_dir = os.path.join(OUT_DIR, str(date.date()))
if not os.path.exists(_dir):
os.makedirs(_dir)
save_time = time.strftime("%Y%m%d-%H%M%S")
Final_LargeDataSetTest_MainFL = pd.DataFrame.from_dict(
Final_LargeDataSetTest_MainFL)
data_Global_main = pd.DataFrame.from_dict(data_Global_main)
Final_LargeDataSetTest_MainFL.to_csv(
os.path.join(
_dir,
f"{save_time}-{args.dataset}-Final_LargeDataSetTest_MainFL.csv"
))
data_Global_main.to_csv(
os.path.join(_dir,
f"{save_time}-{args.dataset}-data_Global_main.csv"))
# Proposed G1
Final_LargeDataSetTest_G1_temp, data_Global_G1_temp = Proposed_G1(
net_glob_G1, dict_workers_index, dict_users_DCFL,
dict_labels_counter_mainFL, args, cost, dataset_train,
dataset_test, small_shared_dataset, loss_main, R_G1, optimal_delay)
Final_LargeDataSetTest_G1 = merge(Final_LargeDataSetTest_G1,
Final_LargeDataSetTest_G1_temp)
data_Global_G1 = merge(data_Global_G1, data_Global_G1_temp)
Final_LargeDataSetTest_G1 = pd.DataFrame.from_dict(
Final_LargeDataSetTest_G1)
data_Global_G1 = pd.DataFrame.from_dict(data_Global_G1)
Final_LargeDataSetTest_G1.to_csv(
os.path.join(
_dir,
f"{save_time}-{args.dataset}-Final_LargeDataSetTest_G1.csv"))
data_Global_G1.to_csv(
os.path.join(_dir,
f"{save_time}-{args.dataset}-data_Global_G1.csv"))
print("G1 alg is done")
def main():
# parse args
args = args_parser()
os.environ["CUDA_VISIBLE_DEVICES"] = args.gpu
dataPath = args.datasetPath
# random seed
np.random.seed(args.seed)
cudnn.benchmark = False
cudnn.deterministic = True
torch.manual_seed(args.seed)
cudnn.enabled = True
torch.cuda.manual_seed(args.seed)
# load dataset and split users
if args.dataset == 'cifar10':
_CIFAR_TRAIN_TRANSFORMS = [
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)),
]
dataset_train = datasets.CIFAR10(
dataPath,
train=True,
download=True,
transform=transforms.Compose(_CIFAR_TRAIN_TRANSFORMS))
_CIFAR_TEST_TRANSFORMS = [
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)),
]
dataset_test = datasets.CIFAR10(
dataPath,
train=False,
transform=transforms.Compose(_CIFAR_TEST_TRANSFORMS))
if args.iid == 0: # IID
dict_users = cifar_iid(dataset_train, args.num_users)
elif args.iid == 2: # non-IID
dict_users = cifar_noniid_2(dataset_train, args.num_users)
else:
exit('Error: unrecognized class')
elif args.dataset == 'emnist':
_MNIST_TRAIN_TRANSFORMS = _MNIST_TEST_TRANSFORMS = [
transforms.ToTensor(),
transforms.ToPILImage(),
transforms.Pad(2),
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
]
dataset_train = datasets.EMNIST(
dataPath,
train=True,
download=True,
transform=transforms.Compose(_MNIST_TRAIN_TRANSFORMS),
split='letters')
dataset_test = datasets.EMNIST(
dataPath,
train=False,
download=True,
transform=transforms.Compose(_MNIST_TEST_TRANSFORMS),
split='letters')
dict_users = femnist_star(dataset_train, args.num_users)
elif args.dataset == 'cifar100':
_CIFAR_TRAIN_TRANSFORMS = [
transforms.RandomCrop(32, padding=4),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)),
]
dataset_train = datasets.CIFAR100(
dataPath,
train=True,
download=True,
transform=transforms.Compose(_CIFAR_TRAIN_TRANSFORMS))
_CIFAR_TEST_TRANSFORMS = [
transforms.ToTensor(),
transforms.Normalize((0.4914, 0.4822, 0.4465),
(0.2023, 0.1994, 0.2010)),
]
dataset_test = datasets.CIFAR100(
dataPath,
train=False,
transform=transforms.Compose(_CIFAR_TEST_TRANSFORMS))
if args.iid == 0: # IID
dict_users = cifar_100_iid(dataset_train, args.num_users)
elif args.iid == 2: # non-IID
dict_users = cifar_100_noniid(dataset_train, args.num_users)
else:
exit('Error: unrecognized dataset')
# build model
if args.dataset == 'cifar10':
if args.model == "CNNStd5":
net_glob = CNNCifarStd5().cuda()
else:
exit('Error: unrecognized model')
elif args.dataset == 'emnist':
if args.model == "CNNStd5":
net_glob = CNNEmnistStd5().cuda()
else:
exit('Error: unrecognized model')
elif args.dataset == 'cifar100':
if args.model == "CNNStd5":
net_glob = CNNCifar100Std5().cuda()
else:
exit('Error: unrecognized model')
else:
exit('Error: unrecognized model')
print('Number of model parameters: {}'.format(
sum([p.data.nelement() for p in net_glob.parameters()])))
net_glob.train()
learning_rate = args.lr
test_acc = []
avg_loss = []
# Train
for iter in range(args.epochs):
m = max(int(args.frac * args.num_users), 1)
idxs_users = np.random.choice(range(args.num_users), m, replace=False)
w_locals, loss_locals = [], []
for i, idx in enumerate(idxs_users):
print('user: {:d}'.format(idx))
local = LocalUpdate(args=args,
dataset=dataset_train,
idxs=dict_users[idx])
w, loss = local.train(model=copy.deepcopy(net_glob).cuda(),
lr=learning_rate)
w_locals.append(copy.deepcopy(w))
loss_locals.append(copy.deepcopy(loss))
# update global weights
w_glob = FedAvg(w_locals)
# copy weight to net_glob
net_glob.load_state_dict(w_glob)
# print loss
loss_avg = sum(loss_locals) / len(loss_locals)
print('Round {:3d}, Average loss {:.6f}'.format(iter, loss_avg))
acc_test, _ = test_img(net_glob.cuda(), dataset_test, args)
print("test accuracy: {:.4f}".format(acc_test))
test_acc.append(acc_test)
avg_loss.append(loss_avg)
learning_rate = adjust_learning_rate(learning_rate, args.lr_drop)
filename = './accuracy-' + str(args.dataset) + '-iid' + str(args.iid) + '-' + str(args.epochs) + '-seed' \
+ str(args.seed) + '-' + str(args.loss_type) + '-beta' + str(args.beta) + '-mu' + str(args.mu)
save_result(test_acc, avg_loss, filename)
def modelBuild():
"""
Build the basic training network and return the related args.
"""
# build model
args = args_parser()
args.device = torch.device('cuda:{}'.format(
args.gpu) if torch.cuda.is_available() and args.gpu != -1 else 'cpu')
# load dataset and split users
if args.dataset == 'mnist':
trans_mnist = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307, ), (0.3081, ))
])
dataset_train = datasets.MNIST('../data/mnist/',
train=True,
download=True,
transform=trans_mnist)
dataset_test = datasets.MNIST('../data/mnist/',
train=False,
download=True,
transform=trans_mnist)
# sample users
if args.iid:
# allocate the dataset index to users
dict_users = mnist_iid(dataset_train, args.num_users)
else:
dict_users = mnist_noniid(dataset_train, args.num_users)
elif args.dataset == 'cifar':
trans_cifar = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])
dataset_train = datasets.CIFAR10('../data/cifar',
train=True,
download=True,
transform=trans_cifar)
dataset_test = datasets.CIFAR10('../data/cifar',
train=False,
download=True,
transform=trans_cifar)
if args.iid:
dict_users = cifar_iid(dataset_train, args.num_users)
else:
exit('Error: only consider IID setting in CIFAR10')
else:
exit('Error: unrecognized dataset')
print("The para of iid is " + str(args.iid))
img_size = dataset_train[0][0].shape
if args.model == 'cnn' and args.dataset == 'cifar':
net_glob = CNNCifar(args=args).to(args.device)
elif args.model == 'cnn' and args.dataset == 'mnist':
net_glob = CNNMnist(args=args).to(args.device)
elif args.model == 'mlp':
len_in = 1
for x in img_size:
len_in *= x
net_glob = MLP(dim_in=len_in, dim_hidden=200,
dim_out=args.num_classes).to(args.device)
else:
exit('Error: unrecognized model')
print("********************************")
print(net_glob)
print("********************************")
return net_glob, args, dataset_train, dataset_test, dict_users
def main():
# parse args
args = args_parser()
args.device = torch.device('cuda:{}'.format(args.gpu) if torch.cuda.is_available() and args.gpu != -1 else 'cpu')
# load dataset and split users
if args.dataset == 'mnist':
trans_mnist = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
dataset_train = datasets.MNIST('../data/mnist/', train=True, download=True, transform=trans_mnist)
dataset_test = datasets.MNIST('../data/mnist/', train=False, download=True, transform=trans_mnist)
# sample users
if args.iid:
dict_users = mnist_iid(dataset_train, args.num_users)
else:
dict_users, dict_labels_counter = mnist_noniid(dataset_train, args.num_users)
dict_users_mainFL, dict_labels_counter_mainFL = dict_users, dict_labels_counter
elif args.dataset == 'cifar':
trans_cifar = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])
dataset_train = datasets.CIFAR10('../data/cifar', train=True, download=True, transform=trans_cifar)
dataset_test = datasets.CIFAR10('../data/cifar', train=False, download=True, transform=trans_cifar)
if args.iid:
dict_users = cifar_iid(dataset_train, args.num_users)
else:
dict_users, dict_labels_counter = cifar_noniid(dataset_train, args.num_users)
dict_users_mainFL, dict_labels_counter_mainFL = dict_users, dict_labels_counter
elif args.dataset == 'fmnist':
trans_fmnist = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))])
dataset_train = datasets.FashionMNIST('../data/fmnist', train=True, download=True, transform=trans_fmnist)
dataset_test = datasets.FashionMNIST('../data/fmnist', train=False, download=True, transform=trans_fmnist)
if args.iid:
dict_users = mnist_iid(dataset_train, args.num_users)
else:
dict_users, dict_labels_counter = mnist_noniid(dataset_train, args.num_users)
dict_users_mainFL, dict_labels_counter_mainFL = dict_users, dict_labels_counter
else:
exit('Error: unrecognized dataset')
img_size = dataset_train[0][0].shape
acc_full_distributed = []
acc_full_main = []
loss_full_ditributed = []
loss_full_main = []
SD_acc_full_distributed = []
SD_acc_full_main = []
SD_loss_full_ditributed = []
SD_loss_full_main = []
workers_percent_full_distributed = []
workers_percent_full_main = []
variable_start = 0.1
variable_end = 1.0
while_counter = 0.1
counter_array = []
Accuracy_Fraction = []
Workers_Fraction = []
accuracy_fraction_each_round_newFL = 0
workers_fraction_each_round_newFL = 0
accuracy_fraction_each_round_mainFL = 0
workers_fraction_each_round_mainFL = 0
data_main = {}
data_DCFL = {}
data_Global_main = {"C": [], "Round":[], "Average Loss Train": [], "Average Loss Test": [], "Accuracy Test": [],
"Workers Number": [], "Large Test Loss":[], "Large Test Accuracy":[]}
data_Global_DCFL = {"C": [], "Round":[], "Average Loss Train": [], "Average Loss Test": [], "Accuracy Test": [],
"Workers Number": [], "Large Test Loss":[], "Large Test Accuracy":[]}
Final_LargeDataSetTest_DCFL = {"C":[], "Test Accuracy":[], "Test Loss":[], "Train Loss":[], "Train Accuracy":[],
"Total Rounds":[]}
Final_LargeDataSetTest_MainFL = {"C":[], "Test Accuracy": [], "Test Loss": [], "Train Loss": [], "Train Accuracy":[]}
# build model
args.frac = variable_start
test_ds, valid_ds_before = torch.utils.data.random_split(dataset_test, (9500, 500))
valid_ds = create_shared_dataset(valid_ds_before, 200)
#while variable_start <= variable_end:
for c_counter in range(1, 11, 3):
if args.model == 'cnn' and args.dataset == 'cifar':
net_glob = CNNCifar(args=args).to(args.device)
net_glob_mainFL = copy.deepcopy(net_glob)
elif args.model == 'cnn' and args.dataset == 'mnist':
net_glob = CNNMnist(args=args).to(args.device)
net_glob_mainFL = copy.deepcopy(net_glob)
elif args.model == 'cnn' and args.dataset == 'fmnist':
net_glob = CNNFashion_Mnist(args=args).to(args.device)
net_glob_mainFL = copy.deepcopy(net_glob)
elif args.model == 'mlp':
len_in = 1
for x in img_size:
len_in *= x
net_glob = MLP(dim_in=len_in, dim_hidden=200, dim_out=args.num_classes).to(args.device)
else:
exit('Error: unrecognized model')
counter_array.append((c_counter/10))
args.frac = (c_counter/10)
######saving index of workers
dict_workers_index = defaultdict(list)
#############Main FL
w_glob_mainFL = net_glob_mainFL.state_dict()
loss_train_mainFL = []
# cv_loss_2, cv_acc_2 = [], []
# val_loss_pre_2, counter_2 = 0, 0
# net_best_2 = None
# best_loss_2 = None
# val_acc_list_2, net_list_2 = [], []
Loss_local_each_global_total_mainFL = []
Accuracy_local_each_global_total_mainFL = []
loss_workers_total_mainFL = np.zeros(shape=(args.num_users, args.epochs))
label_workers_mainFL = {i: np.array([], dtype='int64') for i in range(args.num_users)}
validation_test_mainFed = []
acc_test, loss_test = test_img(net_glob_mainFL, dataset_test, args)
workers_participation_main_fd = np.zeros((args.num_users, args.epochs))
workers_percent_main = []
# for iter in range(args.epochs):
net_glob_mainFL.eval()
acc_test_final_mainFL, loss_test_final_mainFL = test_img(net_glob_mainFL, dataset_test, args)
while_counter_mainFL = loss_test_final_mainFL
iter_mainFL = 0
workers_mainFL = []
for i in range(args.num_users):
workers_mainFL.append(i)
temp_netglob_mainFL = net_glob_mainFL
while iter_mainFL < (args.epochs/2):
data_main['round_{}'.format(iter_mainFL)] = []
# data_Global_main['round_{}'.format(iter)] = []
# print("round started")
Loss_local_each_global_mainFL = []
loss_workers_mainFL = np.zeros((args.num_users, args.epochs))
w_locals_mainFL, loss_locals_mainFL = [], []
m_mainFL = max(int(args.frac * args.num_users), 1)
idxs_users_mainFL = np.random.choice(range(args.num_users), m_mainFL, replace=False)
list_of_random_workers = random.sample(workers_mainFL, m_mainFL)
for i in range(len(list_of_random_workers)):
dict_workers_index[iter_mainFL].append(list_of_random_workers[i])
x_mainFL = net_glob_mainFL
x_mainFL.eval()
acc_test_global_mainFL, loss_test_global_mainFL = test_img(x_mainFL, valid_ds, args)
Loss_local_each_global_total_mainFL.append(loss_test_global_mainFL)
Accuracy_local_each_global_total_mainFL.append(acc_test_global_mainFL)
SD_acc_full_main.append(acc_test_global_mainFL)
SD_loss_full_main.append(loss_test_global_mainFL)
workers_count_mainFL = 0
temp_accuracy = np.zeros(1)
temp_loss_test = np.zeros(1)
temp_loss_train = np.zeros(1)
for idx in list_of_random_workers:
# print("train started")
local_mainFL = LocalUpdate(args=args, dataset=dataset_train, idxs=dict_users_mainFL[idx])
w_mainFL, loss_mainFL = local_mainFL.train(net=copy.deepcopy(net_glob_mainFL).to(args.device))
# print(w)
# print("train completed")
w_locals_mainFL.append(copy.deepcopy(w_mainFL))
loss_locals_mainFL.append(copy.deepcopy(loss_mainFL))
# temp = FedAvg(w)
temp_netglob_mainFL.load_state_dict(w_mainFL)
temp_netglob_mainFL.eval()
print(pnorm_2(temp_netglob_mainFL, 2))
acc_test_local_mainFL, loss_test_local_mainFL = test_img(temp_netglob_mainFL, valid_ds, args)
temp_accuracy[0] = acc_test_local_mainFL
temp_loss_test[0] = loss_test_local_mainFL
temp_loss_train[0] = loss_mainFL
loss_workers_total_mainFL[idx, iter_mainFL] = acc_test_local_mainFL
workers_participation_main_fd[idx][iter_mainFL] = 1
workers_count_mainFL += 1
data_main['round_{}'.format(iter_mainFL)].append({
'C': args.frac,
'User ID': idx,
# 'Local Update': copy.deepcopy(w_mainFL),
'Loss Train': temp_loss_train[0],
'Loss Test': temp_loss_test[0],
'Accuracy': temp_accuracy[0]
})
# update global weights
w_glob_mainFL = FedAvg(w_locals_mainFL)
# copy weight to net_glob
net_glob_mainFL.load_state_dict(w_glob_mainFL)
# print("round completed")
loss_avg_mainFL = sum(loss_locals_mainFL) / len(loss_locals_mainFL)
# print('Round {:3d}, Average loss {:.3f}'.format(iter, loss_avg_mainFL))
loss_train_mainFL.append(loss_avg_mainFL)
# print("round completed")
acc_test_round_mainfed, loss_test_round_mainfed = test_img(net_glob_mainFL, dataset_test, args)
validation_test_mainFed.append(acc_test_round_mainfed)
workers_percent_main.append(workers_count_mainFL / args.num_users)
# plot workers percent of participating
print(iter_mainFL, " round main fl finished")
acc_test_final_mainFL, loss_test_final_mainFL = test_img(net_glob_mainFL, dataset_test, args)
while_counter_mainFL = loss_test_final_mainFL
data_Global_main["Round"].append(iter_mainFL)
data_Global_main["C"].append(args.frac)
data_Global_main["Average Loss Train"].append(float(loss_avg_mainFL))
data_Global_main["Average Loss Test"].append(float(loss_test_global_mainFL))
data_Global_main["Accuracy Test"].append(float(acc_test_global_mainFL))
data_Global_main["Workers Number"].append(float(workers_count_mainFL))
data_Global_main["Large Test Loss"].append(float(loss_test_final_mainFL))
data_Global_main["Large Test Accuracy"].append(float(acc_test_final_mainFL))
iter_mainFL = iter_mainFL + 1
workers_percent_final_mainFL = np.zeros(args.num_users)
workers_name_mainFL = np.empty(args.num_users)
for i in range(len(workers_participation_main_fd[:, 1])):
workers_percent_final_mainFL[i] = sum(workers_participation_main_fd[i, :]) / args.epochs
workers_name_mainFL[i] = i
net_glob_mainFL.eval()
# print("train test started")
acc_train_final_main, loss_train_final_main = test_img(net_glob_mainFL, dataset_train, args)
# print("train test finished")
acc_test_final_main, loss_test_final_main = test_img(net_glob_mainFL, dataset_test, args)
Final_LargeDataSetTest_MainFL["C"].append(args.frac)
Final_LargeDataSetTest_MainFL["Test Loss"].append(float(loss_test_final_main))
Final_LargeDataSetTest_MainFL["Test Accuracy"].append(float(acc_test_final_main))
Final_LargeDataSetTest_MainFL["Train Loss"].append(float(loss_train_final_main))
Final_LargeDataSetTest_MainFL["Train Accuracy"].append(float(acc_train_final_main))
# copy weights
w_glob = net_glob.state_dict()
temp_after = copy.deepcopy(net_glob)
temp_before = copy.deepcopy(net_glob)
# training
loss_train = []
# cv_loss, cv_acc = [], []
# val_loss_pre, counter = 0, 0
# net_best = None
# best_loss = None
# val_acc_list, net_list = [], []
Loss_local_each_global_total = []
# valid_ds = create_shared_dataset(dataset_test, 500)
loss_workers_total = np.zeros(shape=(args.num_users, args.epochs))
label_workers = {i: np.array([], dtype='int64') for i in range(args.num_users)}
workers_percent_dist = []
validation_test_newFed = []
workers_participation = np.zeros((args.num_users, args.epochs))
workers = []
for i in range(args.num_users):
workers.append(i)
counter_threshold_decrease = np.zeros(args.epochs)
Global_Accuracy_Tracker = np.zeros(args.epochs)
Global_Loss_Tracker = np.zeros(args.epochs)
threshold = 0.5
alpha = 0.5 ##decrease parameter
beta = 0.1 ##delta accuracy controller
gamma = 0.5 ##threshold decrease parameter
Goal_Loss = float(loss_test_final_main)
#for iter in range(args.epochs):
net_glob.eval()
acc_test_final, loss_test_final = test_img(net_glob, dataset_test, args)
while_counter = float(loss_test_final)
iter = 0
total_rounds_dcfl = 0
while (while_counter + 0.01) > Goal_Loss and iter <= args.epochs:
data_DCFL['round_{}'.format(iter)] = []
Loss_local_each_global = []
loss_workers = np.zeros((args.num_users, args.epochs))
w_locals, loss_locals = [], []
m = max(int(args.frac * args.num_users), 1)
idxs_users = np.random.choice(range(args.num_users), m, replace=False)
counter_threshold = 0
print(iter, " in dist FL started")
#if iter % 5 == 0:
x = copy.deepcopy(net_glob)
x.eval()
acc_test_global, loss_test_global = test_img(x, valid_ds, args)
Loss_local_each_global_total.append(acc_test_global)
Global_Accuracy_Tracker[iter] = acc_test_global
Global_Loss_Tracker[iter] = loss_test_global
if iter > 0 & (Global_Loss_Tracker[iter-1] - Global_Loss_Tracker[iter] <= beta):
threshold = threshold - gamma
if threshold == 0.0:
threshold = 1.0
print("threshold decreased to", threshold)
workers_count = 0
SD_acc_full_distributed.append(acc_test_global)
SD_loss_full_ditributed.append(loss_test_global)
temp_w_locals = []
temp_workers_loss = np.empty(args.num_users)
temp_workers_accuracy = np.empty(args.num_users)
temp_workers_loss_test = np.empty(args.num_users)
temp_workers_loss_differenc = np.empty(args.num_users)
temp_workers_accuracy_differenc = np.empty(args.num_users)
flag = np.zeros(args.num_users)
list_of_random_workers_newfl = []
if iter < (args.epochs/2):
for key, value in dict_workers_index.items():
# print(value)
if key == iter:
list_of_random_workers_newfl = dict_workers_index[key]
else:
list_of_random_workers_newfl = random.sample(workers, m)
for idx in list_of_random_workers_newfl:
#print("train started")
# before starting train
temp_before = copy.deepcopy(net_glob)
# temp_before.load_state_dict(w)
temp_before.eval()
acc_test_local_before, loss_test_local_before = test_img(temp_before, valid_ds, args)
local = LocalUpdate(args=args, dataset=dataset_train, idxs=dict_users[idx])
w, loss = local.train(net=copy.deepcopy(net_glob).to(args.device))
#print(w)
#print("train completed")
#print("type of idx is ", type(temp_w_locals))
temp_w_locals.append(copy.deepcopy(w))
temp_workers_loss[idx] = copy.deepcopy(loss)
temp_after = copy.deepcopy(net_glob)
temp_after.load_state_dict(w)
temp_after.eval()
acc_test_local_after, loss_test_local_after = test_img(temp_after, valid_ds, args)
loss_workers_total[idx, iter] = loss_test_local_after
temp_workers_accuracy[idx] = acc_test_local_after
temp_workers_loss_test[idx] = loss_test_local_after
temp_workers_loss_differenc[idx] = loss_test_local_before - loss_test_local_after
temp_workers_accuracy_differenc[idx] = acc_test_local_after - acc_test_local_before
print("train finished")
while len(w_locals) < 1:
#print("recieving started")
index = 0
for idx in list_of_random_workers_newfl:
#print("acc is ", temp_workers_accuracy[idx])
# print(temp_workers_loss_differenc)
if workers_count >= m:
break
elif temp_workers_loss_differenc[idx] >= (threshold) \
and temp_workers_loss_differenc[idx] > 0 \
and flag[idx]==0:
print("Update Received")
w_locals.append(copy.deepcopy(temp_w_locals[index]))
#print(temp_w_locals[index])
loss_locals.append(temp_workers_loss[idx])
flag[idx] = 1
workers_count += 1
workers_participation[idx][iter] = 1
data_DCFL['round_{}'.format(iter)].append({
'C': args.frac,
'User ID': idx,
'Loss Train': loss_workers_total[idx, iter],
'Loss Test': temp_workers_loss[idx],
'Accuracy': temp_workers_accuracy[idx]
})
index += 1
if len(w_locals) < 1:
threshold = threshold / 2
if threshold == -np.inf:
threshold = 1
print("threshold increased to ", threshold)
# update global weights
w_glob = FedAvg(w_locals)
# copy weight to net_glob
net_glob.load_state_dict(w_glob)
#print("round completed")
loss_avg = sum(loss_locals) / len(loss_locals)
loss_train.append(loss_avg)
workers_percent_dist.append(workers_count/args.num_users)
counter_threshold_decrease[iter] = counter_threshold
print(iter, " round dist fl finished")
acc_test_final, loss_test_final = test_img(net_glob, dataset_test, args)
while_counter = loss_test_final
data_Global_DCFL["Round"].append(iter)
data_Global_DCFL["C"].append(args.frac)
data_Global_DCFL["Average Loss Train"].append(loss_avg)
data_Global_DCFL["Accuracy Test"].append(Global_Accuracy_Tracker[iter])
data_Global_DCFL["Average Loss Test"].append(Global_Loss_Tracker[iter])
data_Global_DCFL["Workers Number"].append(workers_count)
data_Global_DCFL["Large Test Loss"].append(float(loss_test_final))
data_Global_DCFL["Large Test Accuracy"].append(float(acc_test_final))
total_rounds_dcfl = iter
iter = iter + 1
#plot workers percent of participating
workers_percent_final = np.zeros(args.num_users)
workers_name = np.empty(args.num_users)
#print(workers_participation)
for i in range(len(workers_participation[:, 1])):
workers_percent_final[i] = sum(workers_participation[i, :])/args.epochs
workers_name[i] = i
workers_fraction_each_round_newFL = sum(workers_percent_final)/len(workers_percent_final)
# testing
#print("testing started")
net_glob.eval()
#print("train test started")
acc_train_final, loss_train_final = test_img(net_glob, dataset_train, args)
#print("train test finished")
acc_test_final, loss_test_final = test_img(net_glob, dataset_test, args)
acc_full_distributed.append(acc_test_final)
loss_full_ditributed.append(loss_test_final)
Final_LargeDataSetTest_DCFL["C"].append(args.frac)
Final_LargeDataSetTest_DCFL["Test Loss"].append(float(loss_test_final))
Final_LargeDataSetTest_DCFL["Test Accuracy"].append(float(acc_test_final))
Final_LargeDataSetTest_DCFL["Train Loss"].append(float(loss_train_final))
Final_LargeDataSetTest_DCFL["Train Accuracy"].append(float(acc_train_final))
Final_LargeDataSetTest_DCFL["Total Rounds"].append(int(total_rounds_dcfl))
variable_start = variable_start + while_counter
print("C is ", c_counter/10)
with open('CIFAR_100users_data_main_1229-2020.json', 'w') as outfile:
json.dump(data_main, outfile)
with open('CIFAR_100users_data_DCFL_1229-2020.json', 'w') as outfile:
json.dump(data_DCFL, outfile)
with open('CIFAR_100users_data_DCFL_Global_1229-2020.json', 'w') as outfile:
json.dump(data_Global_DCFL, outfile)
with open('CIFAR_100users_data_main_Global_1229-2020.json', 'w') as outfile:
json.dump(data_Global_main, outfile)
with open('Final-CIFAR_100users_data_main_Global_1229-2020.json', 'w') as outfile:
json.dump(Final_LargeDataSetTest_MainFL, outfile)
with open('Final-CIFAR_100users_data_DCFL_Global_1229-2020.json', 'w') as outfile:
json.dump(Final_LargeDataSetTest_DCFL, outfile)
return 1
def run_all(clf_all1, clf_all2, adv_all1, adv_all2, adv_all3):
# parse args
args = args_parser()
args.device = torch.device('cuda:{}'.format(
args.gpu) if torch.cuda.is_available() and args.gpu != -1 else 'cpu')
# load ICU dataset and split users
# load ICU data set
X, y, Z = load_ICU_data('../fairness-in-ml/data/adult.data')
if not args.iid:
X = X[:30000]
y = y[:30000]
Z = Z[:30000]
n_points = X.shape[0]
n_features = X.shape[1]
n_sensitive = Z.shape[1]
print(n_features)
# split into train/test set
(X_train, X_test, y_train, y_test, Z_train,
Z_test) = train_test_split(X,
y,
Z,
test_size=0.5,
stratify=y,
random_state=7)
# standardize the data
scaler = StandardScaler().fit(X_train)
scale_df = lambda df, scaler: pd.DataFrame(
scaler.transform(df), columns=df.columns, index=df.index)
X_train = X_train.pipe(scale_df, scaler)
X_test = X_test.pipe(scale_df, scaler)
class PandasDataSet(TensorDataset):
def __init__(self, *dataframes):
tensors = (self._df_to_tensor(df) for df in dataframes)
super(PandasDataSet, self).__init__(*tensors)
def _df_to_tensor(self, df):
if isinstance(df, pd.Series):
df = df.to_frame('dummy')
return torch.from_numpy(df.values).float()
def _df_to_tensor(df):
if isinstance(df, pd.Series):
df = df.to_frame('dummy')
return torch.from_numpy(df.values).float()
train_data = PandasDataSet(X_train, y_train, Z_train)
test_data = PandasDataSet(X_test, y_test, Z_test)
print('# train samples:', len(train_data)) # 15470
print('# test samples:', len(test_data))
batch_size = 32
train_loader = DataLoader(train_data,
batch_size=batch_size,
shuffle=True,
drop_last=True)
test_loader = DataLoader(test_data,
batch_size=len(test_data),
shuffle=True,
drop_last=True)
# sample users
if args.iid:
dict_users_train = fair_iid(train_data, args.num_users)
dict_users_test = fair_iid(test_data, args.num_users)
else:
train_data = [
_df_to_tensor(X_train),
_df_to_tensor(y_train),
_df_to_tensor(Z_train)
]
test_data = [
_df_to_tensor(X_test),
_df_to_tensor(y_test),
_df_to_tensor(Z_test)
]
#import pdb; pdb.set_trace()
dict_users_train, rand_set_all = fair_noniid(train_data,
args.num_users,
num_shards=100,
num_imgs=150,
train=True)
dict_users_test, _ = fair_noniid(test_data,
args.num_users,
num_shards=100,
num_imgs=150,
train=False,
rand_set_all=rand_set_all)
train_data = [
_df_to_tensor(X_train),
_df_to_tensor(y_train),
_df_to_tensor(Z_train)
]
test_data = [
_df_to_tensor(X_test),
_df_to_tensor(y_test),
_df_to_tensor(Z_test)
]
class LocalClassifier(nn.Module):
def __init__(self, n_features, n_hidden=32, p_dropout=0.2):
super(LocalClassifier, self).__init__()
self.network1 = nn.Sequential(nn.Linear(n_features, n_hidden),
nn.ReLU(), nn.Dropout(p_dropout),
nn.Linear(n_hidden, n_hidden),
nn.ReLU(), nn.Dropout(p_dropout),
nn.Linear(n_hidden, n_hidden))
self.network2 = nn.Sequential(nn.ReLU(), nn.Dropout(p_dropout),
nn.Linear(n_hidden, 1))
def forward(self, x):
mid = self.network1(x)
final = torch.sigmoid(self.network2(mid))
return mid, final
def pretrain_classifier(clf, data_loader, optimizer, criterion):
losses = 0.0
for x, y, _ in data_loader:
x = x.to(args.device)
y = y.to(args.device)
clf.zero_grad()
mid, p_y = clf(x)
loss = criterion(p_y, y)
loss.backward()
optimizer.step()
losses += loss.item()
print('loss', losses / len(data_loader))
return clf
def test_classifier(clf, data_loader):
losses = 0
assert len(data_loader) == 1
with torch.no_grad():
for x, y_test, _ in data_loader:
x = x.to(args.device)
mid, y_pred = clf(x)
y_pred = y_pred.cpu()
clf_accuracy = metrics.accuracy_score(y_test,
y_pred > 0.5) * 100
return clf_accuracy
class Adversary(nn.Module):
def __init__(self, n_sensitive, n_hidden=32):
super(Adversary, self).__init__()
self.network = nn.Sequential(
nn.Linear(n_hidden, n_hidden),
nn.ReLU(),
nn.Linear(n_hidden, n_hidden),
nn.ReLU(),
nn.Linear(n_hidden, n_hidden),
nn.ReLU(),
nn.Linear(n_hidden, n_sensitive),
)
def forward(self, x):
return torch.sigmoid(self.network(x))
def pretrain_adversary(adv, clf, data_loader, optimizer, criterion):
losses = 0.0
for x, _, z in data_loader:
x = x.to(args.device)
z = z.to(args.device)
mid, p_y = clf(x)
mid = mid.detach()
p_y = p_y.detach()
adv.zero_grad()
p_z = adv(mid)
loss = (criterion(p_z.to(args.device), z.to(args.device)) *
lambdas.to(args.device)).mean()
loss.backward()
optimizer.step()
losses += loss.item()
print('loss', losses / len(data_loader))
return adv
def test_adversary(adv, clf, data_loader):
losses = 0
adv_accuracies = []
assert len(data_loader) == 1
with torch.no_grad():
for x, _, z_test in data_loader:
x = x.to(args.device)
mid, p_y = clf(x)
mid = mid.detach()
p_y = p_y.detach()
p_z = adv(mid)
for i in range(p_z.shape[1]):
z_test_i = z_test[:, i]
z_pred_i = p_z[:, i]
z_pred_i = z_pred_i.cpu()
adv_accuracy = metrics.accuracy_score(
z_test_i, z_pred_i > 0.5) * 100
adv_accuracies.append(adv_accuracy)
return adv_accuracies
def train_both(clf, adv, data_loader, clf_criterion, adv_criterion,
clf_optimizer, adv_optimizer, lambdas):
# Train adversary
adv_losses = 0.0
for x, y, z in data_loader:
x = x.to(args.device)
z = z.to(args.device)
local, p_y = clf(x)
adv.zero_grad()
p_z = adv(local)
loss_adv = (adv_criterion(p_z.to(args.device), z.to(args.device)) *
lambdas.to(args.device)).mean()
loss_adv.backward()
adv_optimizer.step()
adv_losses += loss_adv.item()
print('adversarial loss', adv_losses / len(data_loader))
# Train classifier on single batch
clf_losses = 0.0
for x, y, z in data_loader:
x = x.to(args.device)
y = y.to(args.device)
z = z.to(args.device)
local, p_y = clf(x)
p_z = adv(local)
clf.zero_grad()
if args.adv:
clf_loss = clf_criterion(p_y.to(args.device), y.to(
args.device)) - (
adv_criterion(p_z.to(args.device), z.to(args.device)) *
lambdas.to(args.device)).mean()
else:
clf_loss = clf_criterion(p_y.to(args.device),
y.to(args.device))
clf_loss.backward()
clf_optimizer.step()
clf_losses += clf_loss.item()
print('classifier loss', clf_losses / len(data_loader))
return clf, adv
def eval_global_performance_text(test_loader_i, global_model, adv_model):
with torch.no_grad():
for test_x, test_y, test_z in test_loader_i:
test_x = test_x.to(args.device)
local_pred, clf_pred = global_model(test_x)
adv_pred = adv_model(local_pred)
y_post_clf = pd.Series(clf_pred.cpu().numpy().ravel(),
index=y_test[list(
dict_users_train[idx])].index)
Z_post_adv = pd.DataFrame(adv_pred.cpu().numpy(),
columns=Z_test.columns)
clf_roc_auc, clf_accuracy, adv_acc1, adv_acc2, adv_roc_auc = _performance_text(
test_y, test_z, y_post_clf, Z_post_adv, epoch=None)
return clf_roc_auc, clf_accuracy, adv_acc1, adv_acc2, adv_roc_auc
lambdas = torch.Tensor([30.0, 30.0])
net_local_list = []
print(
'\n\n======================== STARTING LOCAL TRAINING ========================\n\n\n'
)
for idx in range(args.num_users):
train_data_i_raw = [
torch.FloatTensor(bb[list(dict_users_train[idx])])
for bb in train_data
]
train_data_i = TensorDataset(train_data_i_raw[0], train_data_i_raw[1],
train_data_i_raw[2])
train_loader_i = torch.utils.data.DataLoader(train_data_i,
batch_size=batch_size,
shuffle=False,
num_workers=4)
test_data_i_raw = [
torch.FloatTensor(bb[list(dict_users_train[idx])])
for bb in test_data
]
test_data_i = TensorDataset(test_data_i_raw[0], test_data_i_raw[1],
test_data_i_raw[2])
test_loader_i = torch.utils.data.DataLoader(
test_data_i,
batch_size=len(test_data_i),
shuffle=False,
num_workers=4)
net_local_list.append([train_loader_i, test_loader_i])
class GlobalClassifier(nn.Module):
def __init__(self, n_features, n_hidden=32, p_dropout=0.2):
super(GlobalClassifier, self).__init__()
self.network1 = nn.Sequential(nn.Linear(n_features, n_hidden),
nn.ReLU(), nn.Dropout(p_dropout),
nn.Linear(n_hidden, n_hidden),
nn.ReLU(), nn.Dropout(p_dropout),
nn.Linear(n_hidden, n_hidden))
self.network2 = nn.Sequential(nn.ReLU(), nn.Dropout(p_dropout),
nn.Linear(n_hidden, 1))
def forward(self, x):
mid = self.network1(x)
final = torch.sigmoid(self.network2(mid))
return mid, final
# build global model
global_clf = GlobalClassifier(n_features=n_features).to(args.device)
global_clf_criterion = nn.BCELoss().to(args.device)
global_clf_optimizer = optim.Adam(global_clf.parameters(), lr=0.01)
adv_model = Adversary(Z_train.shape[1]).to(args.device)
adv_criterion = nn.BCELoss(reduce=False).to(args.device)
adv_optimizer = optim.Adam(adv_model.parameters(), lr=0.01)
# copy weights
w_glob = global_clf.state_dict()
adv_glob = adv_model.state_dict()
print(
'\n\n======================== STARTING GLOBAL TRAINING ========================\n\n\n'
)
global_epochs = 10
for iter in range(global_epochs):
w_locals, adv_locals, w_loss_locals, adv_loss_locals = [], [], [], []
for idx in range(args.num_users):
print(
'\n\n======================== GLOBAL TRAINING, ITERATION %d, USER %d ========================\n\n\n'
% (iter, idx))
train_loader_i, test_loader_i = net_local_list[idx]
local = LocalUpdate_noLG(args=args, dataset=train_loader_i)
w, w_loss, adv, adv_loss = local.train(
global_net=copy.deepcopy(global_clf).to(args.device),
adv_model=copy.deepcopy(adv_model).to(args.device),
lambdas=lambdas)
w_locals.append(copy.deepcopy(w))
w_loss_locals.append(copy.deepcopy(w_loss))
adv_locals.append(copy.deepcopy(adv))
adv_loss_locals.append(copy.deepcopy(adv_loss))
w_glob = FedAvg(w_locals)
# copy weight to net_glob
global_clf.load_state_dict(w_glob)
adv_glob = FedAvg(adv_locals)
# copy weight to net_glob
adv_model.load_state_dict(adv_glob)
for idx in range(args.num_users):
train_loader_i, test_loader_i = net_local_list[idx]
print(
'======================== local and global training: evaluating _global_performance_text on device %d ========================'
% idx)
clf_roc_auc, clf_accuracy, adv_acc1, adv_acc2, adv_roc_auc = eval_global_performance_text(
test_loader_i, global_clf, adv_model)
print(
'======================== by now the global classifier should work better than local classifier ========================'
)
clf_all1.append(clf_roc_auc)
clf_all2.append(clf_accuracy)
adv_all1.append(adv_acc1)
adv_all2.append(adv_acc2)
adv_all3.append(adv_roc_auc)
print('clf_all1', np.mean(np.array(clf_all1)), np.std(np.array(clf_all1)))
print('clf_all2', np.mean(np.array(clf_all2)), np.std(np.array(clf_all2)))
print('adv_all1', np.mean(np.array(adv_all1)), np.std(np.array(adv_all1)))
print('adv_all2', np.mean(np.array(adv_all2)), np.std(np.array(adv_all2)))
print('adv_all3', np.mean(np.array(adv_all3)), np.std(np.array(adv_all3)))
return clf_all1, clf_all2, adv_all1, adv_all2, adv_all3