A complex network link prediction method and system based on logical reasoning and graph convolution

Abstract

The invention discloses a complex network link prediction method and system based on logical reasoning and graph convolution. The method includes: constructing a knowledge graph corresponding to a complex network, and obtaining a training set; performing relational reasoning on each entity pair in the training set through a default first-order logical inference network, and obtaining a relational confidence matrix through mapping; based on relational confidence degree matrix, iteratively trains the graph convolutional neural network based on iterative attention through the centralized training decentralized execution mechanism and the local relationship attention mechanism, and obtains the first probability distribution; calculates according to the relationship weight matrix and relationship confidence matrix output by the network iteration The second probability distribution; obtain the Wasserstein distance between the first probability distribution and the second probability distribution according to the joint evaluation function; iteratively update the two networks according to the Wasserstein distance to obtain a link prediction model; complete the knowledge graph according to the link prediction model. The link prediction efficiency of the present invention is high.

Description

technical field [0001] The invention belongs to the technical field of complex network analysis, and in particular relates to a complex network link prediction method and system based on logical reasoning and graph convolution. Background technique [0002] A complex network is an abstraction of real networks such as social networks, citation networks, biological metabolism networks, and cooperative relationship networks. Most of the problems in the knowledge graph can be expressed in the form of networks. To build a complete complex network, it can be combined with the knowledge graph. Do it through link prediction. The task of link prediction is to predict missing edges in complex networks, or to predict edges that may appear in the future, while knowledge graphs store complex relationships between entities and entities, including a large number of fact triples composed of entities and relationships between entities, but In large-scale knowledge graphs, due to the sparsen...

AI Technical Summary

Problems solved by technology

The link prediction task is to predict the missing edges in the complex network, or predict the edges that may appear in the future, and the knowledge graph stores the complex relationship between entities and entities, including a large number of fact triples composed of entities and the relationship between entities, but In large-scale knowledge graphs, due to the sparsity of data, knowledge is incomplete, and there are many hidden knowledge that have not been mined, so link prediction tasks are required

The existing complex network link prediction methods often use R-GCN (Relational Graph Convolutional Network, relational graph convolutional network), but the link prediction performance of R-GCN is low

Images