Federal transfer learning-based model training method and computing node

Abstract

The invention discloses a federal transfer learning-based model training method and a computational node, which can be applied to the field of artificial intelligence, and the method comprises the following steps: training a model parameter G of a feature extractor and a model parameter T of a subtask model (such as a classifier) on each source domain through local labeled data, sending all G to a target domain, training a model parameter D1 of a domain discriminator on each source domain, training a model parameter D2 of the domain discriminator on the target domain, aggregating all D1 and D2 at a server side or a target domain side to obtain an aggregation parameter value D, and sending D to each source domain, and performing repeated iterative adversarial training on each source domain through the respective feature extractor and discriminator. According to the method, domain alignment is achieved through the adversarial training process, only model parameter values are transmitted among the domains, data or data features are not transmitted, data privacy is protected, and collaborative training of the models is achieved under the condition that domain alignment and data privacy are considered.

Description

technical field [0001] This application relates to the field of artificial intelligence, in particular to a model training method and computing nodes based on federated transfer learning. Background technique [0002] Federated learning (federated learning, FL) is also known as federated machine learning, federated learning, federated learning, etc., which can effectively help multiple computing nodes to meet the requirements of user privacy protection, data security, and government regulations for data usage and machine learning. Learning modeling; transfer learning (transfer learning, TL) is to use the model developed for task A as the initial point, and reuse it in the process of developing the model for task B, that is, learn the model based on the existing task training. Knowledge is transferred to new tasks to help the model retrain. [0003] There are currently several model training methods based on federated learning / migration learning in the industry. One federate...

AI Technical Summary

Problems solved by technology

[0004] However, the above schemes have flaws. FedAvg can protect user privacy well, but because there is no alignment between the source domain data and the target domain data, the model performance is relatively poor when there is a difference in the distribution of data between different domains; ADDA Contrary to FedAvg, it considers domain alignment, but because the data features extracted from different domains are merged together for retraining, the transferred features themselves still reveal data privacy to a certain extent

Images