Rapid network characterization learning algorithm based on width learning system

Abstract

The invention discloses a rapid network representation learning algorithm based on a width learning system. The method comprises the following steps of S1, importing a network graph module based on atext, parsing and storing a network topological structure in a dictionary format, wherein keys in the dictionary represent network nodes, values corresponding to the keys form a list and represent a node sequence at the other end of the edge where the nodes are located; S2, performing random walk on the network nodes to generate a walk sequence; S3, constructing a network representation learning model based on a width learning system, taking the walking sequence generated in the step S2 and a representation vector with the dimension of K as input, generating a feature vector of a network nodein a feature vector layer, and enhancing the nonlinear classification capability of a network representation learning model by introducing an activation function in an enhancement vector layer to finally realize text-based network multi-label classification. A width learning system model is adopted in the algorithm, and representation learning of network nodes can be rapidly completed.

Description

technical field [0001] The invention belongs to the field of natural language processing, and proposes a method for using a breadth learning system to learn network representations and perform multi-label classification on nodes in the network. and generate training data. Background technique [0002] Network representation algorithms based on random walks, such as DeepWalk, use the word2vec method to compare the nodes in the network to words in natural language processing, and compare each connection path in the network to sentences in natural language processing; use SkipGram Algorithms to calculate the connection structure between network nodes and generate vector representations of nodes. It not only reflects the structural characteristics of the connection between the corresponding network node and its surrounding adjacent nodes, but also realizes the low-dimensional vector representation of the node. This provides an idea for using machine learning algorithms to deal...

AI Technical Summary

Problems solved by technology

The disadvantage of this representation is that any two nodes in the network graph are not necessarily connected, and usually a node has only a few neighbors, so its adjacency matrix is ​​a sparse matrix

However, the accuracy of multi-label classification of traditional network representation is relatively low

Images