Federated Machine Learning

[中文]

FATE-ML includes implementation of many common machine learning algorithms on federated learning. All modules are developed in a decoupling modular approach to enhance scalability. Specifically, we provide:

1. Federated Statistic: PSI, Union, Pearson Correlation, etc.
2. Federated Feature Engineering: Feature Sampling, Feature Binning, Feature Selection, etc.
3. Federated Machine Learning Algorithms: LR, GBDT, DNN
4. Model Evaluation: Binary | Multiclass | Regression evaluation
5. Secure Protocol: Provides multiple security protocols for secure multi-party computing and interaction between participants.

Algorithm List

For tutorial on running modules directly(without FATE-Client) with launcher, please refer here.

Algorithm	Module Name	Examples	Description	Data Input	Data Output	Model Input	Model Output
Reader			Component to passing namespace,name to downstream tasks		output_data
PSI	PSI	psi	Compute intersect data set of multiple parties without leakage of difference set information. Mainly used in hetero scenario task.	input_data	output_data
Sampling	Sample	sample	Federated Sampling data so that its distribution become balance in each party.This module supports local and federation scenario.	input_data	output_data
Data Split	DataSplit	data split	Split one data table into 3 tables by given ratio or count, this module supports local and federation scenario	input_data	train_output_data, validate_output_data, test_output_data
Feature Scale	FeatureScale	feature scale	module for feature scaling and standardization.	train_data, test_data	train_output_data, test_output_data	input_model	output_model
Data Statistics	Statistics	statistics	This component will do some statistical work on the data, including statistical mean, maximum and minimum, median, etc.	input_data			output_model
Hetero Feature Binning	HeteroFeatureBinning	hetero feature binning	With binning input data, calculates each column's iv and woe and transform data according to the binned information.	train_data, test_data	train_output_data, test_output_data	input_model	output_model
Hetero Feature Selection	HeteroFeatureSelection	hetero feature selection	Provide 3 types of filters. Each filters can select columns according to user config	train_data, test_data	train_output_data, test_output_data	input_models, input_model	output_model
Coordinated-LR	CoordinatedLR	coordinated LR	Build hetero logistic regression model through multiple parties.	train_data, validate_data, test_data, cv_data	train_output_data, test_output_data, cv_output_datas	input_model, warm_start_model	output_model
Coordinated-LinR	CoordinatedLinR	coordinated LinR	Build hetero linear regression model through multiple parties.	train_data, validate_data, test_data, cv_data	train_output_data, test_output_data, cv_output_datas	input_model, warm_start_model	output_model
Homo-LR	HomoLR	homo lr	Build homo logistic regression model through multiple parties.	train_data, validate_data, test_data, cv_data	train_output_data, test_output_data, cv_output_datas	input_model, warm_start_model	output_model
Homo-NN	HomoNN	homo nn	Build homo neural network model through multiple parties.	train_data, validate_data, test_data, cv_data	train_output_data, test_output_data, cv_output_datas	input_model, warm_start_model	output_model
Hetero-NN	HeteroNN	hetero nn	Build hetero neural network model through multiple parties.	train_data, validate_data, test_data	train_output_data, test_output_data	warm_start_model, input_model	output_model
Hetero Secure Boosting	HeteroSecureBoost	hetero secureboost	Build hetero secure boosting model through multiple parties	train_data, test_data, cv_data	train_output_data, test_output_data, cv_output_datas	warm_start_model, input_model	output_model
Evaluation	Evaluation	evaluation	Output the model evaluation metrics for user.	input_datas
Union	Union	union	Combine multiple data tables into one.	input_datas	output_data
SSHE-LR	SSHELR	SSHE LR	Build hetero logistic regression model through two parties.	train_data, validate_data, test_data, cv_data	train_output_data, test_output_data, cv_output_datas	input_model, warm_start_model	output_model
SSHE-LinR	SSHELinR	SSHE LinR	Build hetero linear regression model through two parties.	train_data, validate_data, test_data, cv_data	train_output_data, test_output_data, cv_output_datas	input_model, warm_start_model	output_model
Feature Correlation	FeatureCorrelation	Feature Correlation	Compute feature correlation locally or in hetero-federated setting.	input_data		input_model	output_model