Abstract: This specification discloses methods, apparatus, devices, and systems for determining a feature effective value of business data. In one implementation, a method includes: obtaining a joint data share of a first participant based on joint data that includes feature values of a plurality of objects corresponding to a plurality of feature terms, obtaining a predictive value share and a model parameter share based on the joint data and a business prediction model, determining, through secure multi-party computation, a correlation data share corresponding to the plurality of participants, and determining, through a significance test method, an effective value of a feature term of the plurality of feature terms.

Abstract: One or more embodiments of the present specification provide privacy protection-based multicollinearity detection methods, apparatuses, and systems. Data alignment is performed by a member device on respective local feature data with other member devices to construct a joint feature matrix. Privacy protection-based multi-party matrix multiplication computation is performed to compute a product matrix of a transposed matrix of the joint feature matrix and the joint feature matrix. An inverse matrix of the product matrix is determined based on respective submatrices of the product matrix. A variance inflation factor of each attribute feature is determined by the member device with the other member devices using respective submatrices of the inverse matrix and the respective local feature data. Multicollinearity is determined by the member device with the other member devices based on fragment data of the variance inflation factor of each attribute feature.

Abstract: Embodiments of this specification provide methods, apparatuses systems, and computer-readable media for data privacy-preserving training of a service prediction model. In an example training process, a member device performs prediction by using the service prediction model and object feature data held by the member device, and determines, by using a prediction result, update parameters used to update model parameters, where the update parameters include sub-parameters for computational layers of the service prediction model; and divides the computational layers into first-type and second-type computational layers using the sub-parameters; and performs privacy processing on sub-parameters of the first-type computational layers, and outputs processed sub-parameters. Processed sub-parameters of member devices can be aggregated into aggregated sub-parameters.

Abstract: This specification discloses methods, apparatus, devices, and systems for determining a feature effective value of business data. In one implementation, a method includes: obtaining a joint data share of a first participant based on joint data that includes feature values of a plurality of objects corresponding to a plurality of feature terms, obtaining a predictive value share and a model parameter share based on the joint data and a business prediction model, determining, through secure multi-party computation, a correlation data share corresponding to the plurality of participants, and determining, through a significance test method, an effective value of a feature term of the plurality of feature terms.

Abstract: This specification provides example computer-implemented methods and apparatuses for jointly updating a service model based on privacy protection. In an example iteration process, a serving party provides, to each data party, global model parameters and a mapping relationship between the data party and N parameter groups obtained by dividing the global model parameters. Each data party updates a local service model by using the global model parameters, and further updates an updated local service model based on local service data, to upload model parameters in a new service model in a parameter group corresponding to the data party to the serving party. Then, the serving party successively fuses received parameter groups to update the global model parameters.

Abstract: A client device determines a local user gradient value based on a current user preference vector and a local item gradient value based on a current item feature vector. The client device updates a user preference vector by using the local user gradient value and updates an item feature vector by using the local item gradient value. The client device determines a neighboring client device based on a predetermined adjacency relationship. The local item gradient value is sent by the client device to the neighboring client device. The client device receives a neighboring item gradient value sent by the neighboring client device. The client device updates the item feature vector by using the neighboring item gradient value. In response to the client device determining that a predetermined iteration stop condition is satisfied, the client device outputs the user preference vector and the item feature vector.

Abstract: A computer-implemented method, medium, and system are disclosed. One example method includes determining multiple model bases by multiple service parties. A respective local service model is constructed by each service party. Respective local training samples are processed by each service party using the respective local service model to determine respective gradient data corresponding to each model basis. The respective gradient data is sent to a server. In response to determining that the first model basis satisfies a gradient update condition, corresponding gradient data of the first model basis received from each service party are combined to obtain global gradient data corresponding to the first model basis. The global gradient data is sent to each service party. Reference parameters in local model basis corresponding to the first model basis are updated by each service party using the global gradient data to train the respective local service model.

Abstract: A computer-implemented method, medium, and system are disclosed. One example computer-implemented method performed by a server includes obtaining training task information from a task party. The training task information includes information about a to-be-pretrained model and information about a to-be-trained target model. A respective task acceptance indication from each of at least one of a plurality of data parties is received to obtain a candidate data party set. The information about the to-be-pretrained model is sent to each data party in the candidate data party set. A respective pre-trained model of each data party is received. A respective performance parameter of the respective pre-trained model of each data party is obtained. One or more target data parties from the candidate data party set is determined. The information about the to-be-trained target model is sent to the one or more target data parties to obtain a target model.

Abstract: One or more embodiments of the present specification provide privacy protection-based multicollinearity detection methods, apparatuses, and systems. Data alignment is performed by a member device on respective local feature data with other member devices to construct a joint feature matrix. Privacy protection-based multi-party matrix multiplication computation is performed to compute a product matrix of a transposed matrix of the joint feature matrix and the joint feature matrix. An inverse matrix of the product matrix is determined based on respective submatrices of the product matrix. A variance inflation factor of each attribute feature is determined by the member device with the other member devices using respective submatrices of the inverse matrix and the respective local feature data. Multicollinearity is determined by the member device with the other member devices based on fragment data of the variance inflation factor of each attribute feature.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media for secure collaborative computation of a matrix product of a first matrix including private data of a first party and a second matrix including private data of the second party by secret sharing without a trusted initializer. One method includes obtaining a first matrix including private data of the first party; generating a first random matrix; identifying a first sub-matrix and a second sub-matrix of the first random matrix; computing first scrambled private data of the first party based on the first matrix, the first random matrix, the first sub-matrix, and the second sub-matrix; receiving second scrambled private data of the second party; computing a first addend of the matrix product; receiving a second addend of the matrix product; and computing the matrix product by summing the first addend and the second addend.

Abstract: A method for training a neural network model includes: at each first member device, obtaining predicted label data according to a first neural network submodel of the first neural network submodel by using private data for model training, and determining model update information of the first neural network submodel according to the predicted label data and real label data; providing, by each first member device, the model update information of the first neural network submodel and local sample distribution information to a second member device; at the second member device, performing neural network model reconstruction, determining an overall sample probability distribution, and allocating a reconstructed neural network model and the overall sample probability distribution to each first member device; and updating the first neural network submodel at each first member device according to a local sample probability distribution, the reconstructed neural network model, and the overall sample probability distrib

Abstract: A computer-implemented method, medium, and system are disclosed. One example method includes determining multiple model bases by multiple service parties. A respective local service model is constructed by each service party. Respective local training samples are processed by each service party using the respective local service model to determine respective gradient data corresponding to each model basis. The respective gradient data is sent to a server. In response to determining that the first model basis satisfies a gradient update condition, corresponding gradient data of the first model basis received from each service party are combined to obtain global gradient data corresponding to the first model basis. The global gradient data is sent to each service party. Reference parameters in local model basis corresponding to the first model basis are updated by each service party using the global gradient data to train the respective local service model.

Abstract: A computer-implemented method, medium, and system are disclosed. One example method includes determining multiple model bases by multiple service parties. A respective local service model is constructed by each service party. Respective local training samples are processed by each service party using the respective local service model to determine respective gradient data corresponding to each model basis. The respective gradient data is sent to a server. In response to determining that the first model basis satisfies a gradient update condition, corresponding gradient data of the first model basis received from each service party are combined to obtain global gradient data corresponding to the first model basis. The global gradient data is sent to each service party. Reference parameters in local model basis corresponding to the first model basis are updated by each service party using the global gradient data to train the respective local service model.

Abstract: A computer-implemented method, medium, and system are disclosed. One example computer-implemented method performed by a server includes obtaining training task information from a task party. The training task information includes information about a to-be-pretrained model and information about a to-be-trained target model. A respective task acceptance indication from each of at least one of a plurality of data parties is received to obtain a candidate data party set. The information about the to-be-pretrained model is sent to each data party in the candidate data party set. A respective pre-trained model of each data party is received. A respective performance parameter of the respective pre-trained model of each data party is obtained. One or more target data parties from the candidate data party set is determined. The information about the to-be-trained target model is sent to the one or more target data parties to obtain a target model.

Abstract: One or more embodiments of the present specification relate to a model reuse-based model prediction method, apparatus, and system. An example method includes, for each reusable prediction model of a plurality of reusable prediction models, using the reusable prediction model to obtain a respective predicted label of the reusable prediction model, by performing secure computing between an owner of to-be-predicted data and an owner of the reusable prediction model. A predicted label of the to-be-predicted data is determined based on each respective predicted label of each reusable prediction model and a model weight of each reusable prediction model, the model weight of each reusable prediction model being a model weight in a data sample set of the owner of the to-be-predicted data.

Abstract: Embodiments of this specification provide a method and an apparatus for training a neural network model. The neural network model includes first neural network submodels located at first member devices. Each first member device uses private data to perform model prediction to obtain predicted label data and determines model update information of the first neural network submodel, and provides the model update information of the first neural network submodel and local sample distribution information to a second member device. The second member device performs neural network model reconstruction according to the model update information of the first neural network submodel of each first member device, determines an overall sample probability distribution according to the local sample distribution information of each first member device, and allocates the reconstructed neural network model and the overall sample probability distribution to each first member device.

Abstract: One or more embodiments of the present specification relate to a method and system for obtaining a jointly trained model based on privacy protection. An example method includes jointly training a first model, by a first device and with a second device, the first device and the second device each holding respective training data that includes first training data with a sample label, and second training data without the sample label. Jointly training the first model includes privately obtaining the first training data, and performing joint model training using the first training data. The second training data is input to the trained first model to obtain a predicted label for the second training data. Jointly training a second model includes privately obtaining labeled training data, and performing joint model training using the first training data, the second training data, and the labeled training data.