Feed Forward Neural Nets (iai_ffnet)

Feedforward neural nets are a type of neural network in which information flows the nodes in a single direction.

Examples of use cases include:

• Classification tasks like image recognition or churn conversion prediction.

• Regression tasks like forecasting revenues and expenses, or determining the relationship between drug dosage and blood pressure

The iai_ffnet model is a feedforward neural network that uses the same activation for each hidden layer.

Example Model Configuration

model_config = {
    "experiment_name": "test_synthetic_tabular",
    "experiment_description": "test_synthetic_tabular",
    "strategy": {"name": "FedAvg", "params": {}},
    "model": {"params": {"input_size": 15, "hidden_layer_sizes": [6, 6, 6], "output_size": 2}},
    "balance_train_datasets": False,
    "ml_task": {
        "type": "classification",
        "params": {
            "loss_weights": None,
        },
    },
    "optimizer": {"name": "SGD", "params": {"learning_rate": 0.2, "momentum": 0.0}},
    "differential_privacy_params": {"epsilon": 4, "max_grad_norm": 7},
    "save_best_model": {
        "metric": "loss",  # to disable this and save model from the last round, set to None
        "mode": "min",
    },
    "seed": 23,  # for reproducibility
}

For more information, see HFL Model Training with a Sample Local Dataset.