Hypergraph convolutional network model and semi-supervised classification method thereof

Abstract

The invention provides a hypergraph convolutional network model and a semi-supervised classification method thereof. The method comprises the following steps: 1, carrying out sparse coding on sample data features of a non-Euclidean structure to form a sample representation coefficient matrix; 2, constructing a hyperedge according to the similarity of the samples, calculating a hyperedge weight, and constructing a hyper-graph model; 3, by means of a hypergraph theory, defining convolution operation on a hypergraph, and constructing a hypergraph convolution network model; 4, defining a semi-supervised learning method on the hypergraph convolutional network, designing a loss function, and predicting category labels of all samples by using category information of a small number of calibrationsamples; 5, respectively making a semi-given label matrix for training, verifying and testing, setting network hyper-parameters, training a network model, and learning a convolution kernel and a regularity factor parameter of the network according to a random gradient descent algorithm; and 6, for given data, predicting an unknown sample category by using the trained model to realize semi-supervised classification.

Description

technical field [0001] The invention belongs to the technical field of data information processing, and in particular relates to a hypergraph convolutional network model and a semi-supervised classification method thereof. Background technique [0002] Recently, the deep convolutional neural network has achieved great success in tasks such as machine learning and computer vision. The main reason is that the discrete convolution operation defined in each network layer calculates the weighted sum of the central pixel and adjacent pixels. Realize the extraction of image spatial features, and optimize the convolution kernel parameters of each layer during the training process, so that the network can adaptively learn the deep features of the image, so the convolutional neural network can be widely used in various recognition tasks. [0003] Classical deep convolutional networks usually deal with European-style data with regular neighbor structures, such as images, videos, etc. H...

AI Technical Summary

Problems solved by technology

[0003] Classical deep convolutional networks usually deal with European-style data with regular neighbor structures, such as images, videos, etc. However, in real problems, there are many data with irregular neighbor structures, such as social networks, information networks, gene Data, protein structure, traffic road network, etc. often have complex topological structures, and different samples have different numbers of neighbors. Classical convolutional neural networks cannot effectively analyze such non-European structure data.

Images