Method and system for multi-label active learning classification

A technology of active learning and classification methods, applied in the field of machine learning, can solve problems that affect the classification accuracy of the classifier, affect the accuracy of labeling, and do not involve the uncertainty of the sample labels to be tested.

CN104881689AActive Publication Date: 2015-09-02ZHANGJIAGANG INST OF IND TECH SOOCHOW UNIV +1
4 Cites 22 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2015-09-02

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides a method and a system for multi-label active learning classification. The method comprises: respectively using a logarithm likehood method to obtain likehood ratio of a labeled sample label pair and using an entropy method to obtain nondeterminacy of a to-be-labeled sample label pair; respectively calculating KL distances of different labels of a plurality of same samples, and weight factors of a plurality of different labels; performing multiplication on each KL distance and the corresponding weight factor, to obtain a corresponding result, adding the plurality of results, to obtain the KL distance sum of the to-be-labeled sample label pair related to the to-be-labeled sample label pair, using the KL distance sum to determine the nondeterminacy of cross labels; determining final nondeterminacy of the to-be-labeled sample label pair; and using the likehood ratio and the final nondeterminacy of the to-be-labeled sample label pair to obtain a new sample label pair training set, and using the new sample label pair training set to train a classifier.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of machine learning, and more specifically, relates to a multi-label active learning classification method and system. Background technique

[0002] With the development of information technology, the importance of multi-label data classification technology is gradually highlighted, so that the application of corresponding multi-label data classification technology is also increasing, for example, semantic annotation of images and videos, biological gene function classification, text classification, etc. . As a modeling tool for ambiguous objects, multi-label learning is a learning method that is more in line with the laws of the real and objective world. Under this framework, each object no longer corresponds to a unique label. The purpose of multi-label learning is to provide Unseen objects are assigned the appropriate label set. Due to the complexity of multi-label classification problems, it ta...

Examples

Embodiment Construction

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0052] Due to the complexity of multi-label classification problems, it takes a lot of time and effort to collect labeled samples when building a classifier model. However, in the real world, it is very rare to obtain labeled sample labels, and like in the multi-label learning framework, each object corresponds to multiple categories, which increases the difficulty of obtaining labeled samples. Active learning is an effective solution to machine learning probl...