Nested meta learning method and system based on federated architecture

Abstract

The invention provides a nested meta-learning method and system based on a federated architecture. The method comprises the steps that m1 clients are selected from N clients, the m1 clients train local model parameters of the m1 clients based on local data of the m1 clients and global model parameters in the current state, and N and m1 are positive integers and N is larger than or equal to m1; the central server updates global model parameters according to the received local model parameters of the m1 clients; m < 2 > clients are selected from the N clients, the m < 2 > clients determine respective global subtasks of the m < 2 > clients based on respective local data and the updated global model parameters and calculate parameter gradients generated by the global subtasks through a learning objective function, m < 2 > is a positive integer, and N is larger than or equal to m < 2 >; and the central server adjusts the updated global model parameters according to the received parameter gradients of the global subtasks of the m2 clients.

Description

technical field [0001] The invention belongs to the field of machine learning, and in particular relates to a nested meta-learning method and system based on a federated architecture. Background technique [0002] Federated learning is a decentralized machine learning architecture designed to learn models from distributed mobile devices, which solves the problem that data centers do not always have access to large-scale training data. In addition, since the data in each mobile device is privacy sensitive, compared with the centralized machine learning model training process, federated learning also has obvious privacy protection advantages. [0003] Small sample learning can quickly grasp new target concepts with only a small amount of data. It aims to explore how to use the knowledge and experience summarized from existing samples to solve new problems when the number of labeled samples of new target categories is very small. Methods. Meta-learning is one of the mainstrea...

AI Technical Summary

Problems solved by technology

Some researchers proposed a personalized federated average algorithm, that is, in the federated average algorithm, each user trains the meta-learning model locally, and then passes the parameters to the server for aggregation to promote the generalization ability of the model, but the performance of the global model and The aggregation speed needs to be improved; a similar research program also includes the federated meta-learning algorithm, that is, the meta-learning algorithm is used in the federated stochastic gradient descent architecture to obtain the local gradient of each user and update the model parameters, but as mentioned above, The federated stochastic gradient descent algorithm requires frequent communication between users and servers, resulting in excessive communication overhead for this scheme

Images