Sample transfer learning method and device

Abstract

The invention provides a sample transfer learning method and device, and the method combines the prediction results of a prediction model of a source field and a prediction model of a target field ona sample in a sample transfer process, and gives full consideration to the impact on the prediction precision of the prediction model of the target field from the sample of the source field. Meanwhile, in the sample migration iteration process, the prediction models of the source domain and the target domain are continuously optimized based on the intermediate state sample set of the source domainand the target domain obtained by migration; and the performance of the prediction model of each iteration is not inferior to the performance of the prediction model in the last iteration, so that the finally migrated sample set of the target field is more beneficial to improving the performance of the prediction task of the target field.

Description

technical field [0001] The present application relates to the technical field of data processing, and more specifically relates to a sample transfer learning method and device. Background technique [0002] Generally speaking, transfer learning is to use existing knowledge to learn new knowledge, and the core is to find the similarity between existing knowledge and new knowledge. In transfer learning, our existing knowledge is called the source domain, and the new knowledge to be learned is called the target domain. The source domain and the target domain are different but related. We need to find and use the correlation between the source domain and the target domain for knowledge transfer to achieve data calibration. [0003] Among them, the goal of sample transfer learning is to find samples that can improve the performance of target domain prediction tasks (such as classification prediction tasks or regression prediction tasks, etc.) from the sample set in the source do...

AI Technical Summary

Problems solved by technology

However, based on the current sample transfer learning method, the sample set of the target field cannot be reliably determined, which leads to the inability to effectively improve the performance of the target field prediction task.

Images