Federated Node Classification Example

Federated Node Classification with FedGCN on the Cora dataset.

(Time estimate: 3 minutes)

Load libraries

import attridict

from fedgraph.federated_methods import run_fedgraph

Specify the Node Classification configuration

config = {
    # Task, Method, and Dataset Settings
    "fedgraph_task": "NC",
    "dataset": "cora",
    "method": "FedGCN",  # Federated learning method, e.g., "FedGCN"
    "iid_beta": 10000,  # Dirichlet distribution parameter for label distribution among clients
    "distribution_type": "average",  # Distribution type among clients
    # Training Configuration
    "global_rounds": 100,
    "local_step": 3,
    "learning_rate": 0.5,
    "n_trainer": 2,
    "batch_size": -1,  # -1 indicates full batch training
    # Model Structure
    "num_layers": 2,
    "num_hops": 1,  # Number of n-hop neighbors for client communication
    # Resource and Hardware Settings
    "gpu": False,
    "num_cpus_per_trainer": 1,
    "num_gpus_per_trainer": 0,
    # Logging and Output Configuration
    "logdir": "./runs",
    # Security and Privacy
    "use_encryption": False,  # Whether to use Homomorphic Encryption for secure aggregation
    # Dataset Handling Options
    "use_huggingface": False,  # Load dataset directly from Hugging Face Hub
    "saveto_huggingface": False,  # Save partitioned dataset to Hugging Face Hub
    # Scalability and Cluster Configuration
    "use_cluster": False,  # Use Kubernetes for scalability if True
}

Run fedgraph method

config = attridict(config)
run_fedgraph(config)

config:  {'fedgraph_task': 'NC', 'dataset': 'cora', 'method': 'FedGCN', 'iid_beta': 10000, 'distribution_type': 'average', 'global_rounds': 100, 'local_step': 3, 'learning_rate': 0.5, 'n_trainer': 2, 'batch_size': -1, 'num_layers': 2, 'num_hops': 1, 'gpu': False, 'num_cpus_per_trainer': 1, 'num_gpus_per_trainer': 0, 'logdir': './runs', 'use_encryption': False, 'use_huggingface': False, 'saveto_huggingface': False, 'use_cluster': False}
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.x to ./data/cora/raw/ind.cora.x...
Downloaded ./data/cora/raw/ind.cora.x
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.tx to ./data/cora/raw/ind.cora.tx...
Downloaded ./data/cora/raw/ind.cora.tx
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.allx to ./data/cora/raw/ind.cora.allx...
Downloaded ./data/cora/raw/ind.cora.allx
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.y to ./data/cora/raw/ind.cora.y...
Downloaded ./data/cora/raw/ind.cora.y
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.ty to ./data/cora/raw/ind.cora.ty...
Downloaded ./data/cora/raw/ind.cora.ty
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.ally to ./data/cora/raw/ind.cora.ally...
Downloaded ./data/cora/raw/ind.cora.ally
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.graph to ./data/cora/raw/ind.cora.graph...
Downloaded ./data/cora/raw/ind.cora.graph
Downloading https://github.com/kimiyoung/planetoid/raw/master/data/ind.cora.test.index to ./data/cora/raw/ind.cora.test.index...
Downloaded ./data/cora/raw/ind.cora.test.index
server aggregates all local neighbor feature sums
clients received feature aggregation from server
global_rounds 100
average_final_test_loss, 0.9797245250940323
Average test accuracy, 0.787