Unsupervised representation learning method and device based on multi-source heterogeneous features

Abstract

The invention discloses an unsupervised representation learning method and device based on multi-source heterogeneous features, and the method comprises the steps: extracting and integrating multi-source heterogeneous data, designing and training a first encoder of structured data features, and carrying out the coding of the structured data through the first encoder, and obtaining a first coding result; designing and training a second encoder with unstructured data features, and encoding the unstructured data by using the second encoder to obtain a second encoding result; processing the first coding result and the second coding result to obtain a multi-source heterogeneous fusion feature for describing the instance; designing a DNN network based on the multi-source heterogeneous fusion features, and training to obtain feature representation vectors of the multi-source heterogeneous fusion features projected to a multi-dimensional space; and performing the tasks of similarity matching, classification and clustering among the instances by using the feature representation vectors. On the basis of an unsupervised condition, discriminative representation learning of an instance level is realized; and more training data and a better network structure are provided.

Description

technical field [0001] This application relates to the technical fields of unsupervised representation learning and big data analysis, and in particular to an unsupervised representation learning method and device based on multi-source heterogeneous features. Background technique [0002] In real life, when learning a complex concept, there is always a shortcut to simplify it. Machine learning models are no exception. If there is a better expression of the original data that has been refined, it can often make subsequent tasks more effective with less effort. This is also the basic idea of ​​representation learning, that is, to find a better representation of the original data to facilitate subsequent tasks (such as classification), which has important practical significance. [0003] Most successful representation learning models are trained through supervised learning, which requires large datasets that are fully labeled for a specific task. However, obtaining labeled da...

AI Technical Summary

Problems solved by technology

[0005] This application provides an unsupervised representation learning method and device based on multi-source heterogeneous features to solve the problems in the prior art that the cost of supervised learning is too high, and the calculation of instance similarity is expensive and difficult

Images