Model Configuration

The model configuration is a JSON object where the user specifies parameters for the GLM and FFNet models. On this page you will find the schema we use to validate model configurations and an example of a completed model configuration for an FFNet.

Schema

Below is the outline for the schema used to validate the model configuration inputs in the integrate.ai UI.

{
  "$schema": "https://json-schema.org/draft-07/schema#",
  "title": "FL Model Config",
  "description": "The model config for an FL model",
  "type": "object",
  "properties": {
    "experiment_name": {
      "type": "string",
      "description": "Experiment Name"
    },
    "experiment_description": {
      "type": "string",
      "description": "Experiment Description"
    },
    "strategy": {
      "type": "object",
      "properties": {
        "name": {
          "enum": [
            "FedAvg"
          ],
          "description": "Name of the FL strategy"
        },
        "params": {
          "type": "object",
          "properties": {
            "fraction_fit": {
              "type": "number",
              "minimum": 0,
              "maximum": 1,
              "description": "Proportion of clients to use for training. If fraction * total_num_users is smaller than min_num_clients set in the session config, then min_num_clients will be used."
            },
            "fraction_eval": {
              "type": "number",
              "minimum": 0,
              "maximum": 1,
              "description": "Proportion of clients to use for evaluation. If fraction * total_num_users is smaller than min_num_clients set in the session config, then min_num_clients will be used."
            },
            "accept_failures": {
              "type": "boolean",
              "description": "Whether to accept failures during training and evaluation. If False, the training process will be stopped when a client fails, otherwise, the failed client will be ignored."
            }
          },
          "additionalProperties": false
        }
      },
      "required": [
        "name",
        "params"
      ]
    },
    "model": {
      "type": "object",
      "description": "Model type and parameters",
      "properties": {
        "params": {
          "type": "object",
          "description": "Model parameters"
        }
      },
      "required": [
        "params"
      ]
    },
    "ml_task": {
      "type": "object",
      "description": "Type of ML task",
      "properties": {
        "type": {
          "enum": [
            "regression",
            "classification",
            "logistic",
            "normal",
            "poisson",
            "gamma",
            "inverseGaussian"
          ]
        },
        "params": {
          "type": "object"
        }
      },
      "required": ["type", "params"],
      "allOf": [
        {
          "if": {
            "properties": { "type": { "enum": ["regression", "classification"] } }
          },
          "then": {
            "properties": { "params": { "type": "object" } }
          }
        },
        {
          "if": {
            "properties": { "type": { "enum": [
              "logistic",
              "normal",
              "poisson",
              "gamma",
              "inverseGaussian"
            ] } }
          },
          "then": {
            "properties": { "params": {
              "type": "object",
              "properties": {
                "alpha": {
                  "type": "number",
                  "minimum": 0
                },
                "l1_ratio": {
                  "type": "number",
                  "minimum": 0,
                  "maximum": 1
                }
              },
              "required": ["alpha", "l1_ratio"]
            } }
          }
        }
      ]
    },
    "optimizer": {
      "type": "object",
      "properties": {
        "name": {
          "enum": [
            "SGD"
          ]
        },
        "params": {
          "type": "object",
          "properties": {
            "learning_rate": {
              "type": "number",
              "minimum": 0,
              "description": "See https://pytorch.org/docs/stable/generated/torch.optim.SGD.html#torch.optim.SGD for details"
            },
            "momentum": {
              "type": "number",
              "minimum": 0,
              "description": "See https://pytorch.org/docs/stable/generated/torch.optim.SGD.html#torch.optim.SGD for details"
            }
          },
          "required": [
            "learning_rate"
          ],
          "additionalProperties": false
        }
      },
      "required": [
        "name",
        "params"
      ],
      "additionalProperties": false
    },
    "differential_privacy_params": {
      "type": "object",
      "properties": {
        "epsilon": {
          "type": "number",
          "minimum": 0,
          "description": "Privacy budget. Larger values correspond to less privacy protection, and potentially better model performance."
        },
        "max_grad_norm": {
          "type": "number",
          "minimum": 0,
          "description": "The upper bound for clipping gradients. A hyper-parameter to tune."
        }
      },
      "required": [
        "epsilon",
        "max_grad_norm"
      ]
    },
    "eval_metrics": {
      "description": "A list of metrics to use for evaluation",
      "type": "array",
      "minItems": 1,
      "items": {}
    }
  },
  "required": [
    "experiment_name",
    "experiment_description",
    "strategy",
    "model",
    "ml_task",
    "optimizer",
    "differential_privacy_params"
  ]
}

Example

Below is an example of a model configuration for a session.

{
	"experiment_name": "Test session",
	"experiment_description": "This is a test session",
	"job_type": "training",
	"strategy": {
		"name": "FedAvg",
		"params": {}
	},
	"model": {
		"type": "FFNet",
		"params": {
			"input_size": 200,
			"hidden_layer_sizes": [
				80,
				40,
				8
			],
			"output_size": 2,
			"hidden_activation": "relu"
		}
	},
	"ml_task": "classification",
	"optimizer": {
		"name": "SGD",
		"params": {
			"learning_rate": 0.03,
			"momentum": 0
		}
	},
	"differential_privacy_params": {
		"epsilon": 1,
		"max_grad_norm": 7,
		"delta": 0.000001
	},
	"eval_metrics": [
		"accuracy",
		"loss",
		"roc_auc"
	]
}