Simple FedGraph Example

Run a simple example of FedGraph.

(Time estimate: 1 minutes)

Load libraries

import sys

sys.path.append("../fedgraph")
import attridict
import yaml

from fedgraph.federated_methods import FedGCN_Train
from fedgraph.utils import federated_data_loader

Load configuration and federated data

with open("config_fedgcn.yaml", "r") as f:
    config = attridict(yaml.safe_load(f))

data = federated_data_loader(config)

config:  {'dataset': 'cora', 'fedtype': 'fedgcn', 'global_rounds': 100, 'local_step': 3, 'learning_rate': 0.5, 'n_trainer': 2, 'num_layers': 2, 'num_hops': 2, 'gpu': False, 'iid_beta': 10000, 'logdir': './runs'}

Run FedGCN method

FedGCN_Train(config, data)

server aggregates all local neighbor feature sums
clients received feature aggregation from server
global_rounds 100
average_final_test_loss, 0.9302511513233185
average_final_test_accuracy, 0.784