Adaptive Dual Channel Convolution Hypergraph Representation Learning for Technological Intellectual Property

TL;DR

This paper introduces an adaptive dual channel convolution hypergraph neural network for modeling complex relationships in technological intellectual property data, capturing higher-order relations often overlooked by traditional methods.

Contribution

It proposes a novel hypergraph neural network with dual channels and attention mechanism to effectively learn from higher-order relations in technological intellectual property data.

Findings

Outperforms existing methods on multiple datasets

Effectively captures higher-order relations in hypergraph data

Demonstrates improved representation learning for technological IP

Abstract

In the age of big data, the demand for hidden information mining in technological intellectual property is increasing in discrete countries. Definitely, a considerable number of graph learning algorithms for technological intellectual property have been proposed. The goal is to model the technological intellectual property entities and their relationships through the graph structure and use the neural network algorithm to extract the hidden structure information in the graph. However, most of the existing graph learning algorithms merely focus on the information mining of binary relations in technological intellectual property, ignoring the higherorder information hidden in non-binary relations. Therefore, a hypergraph neural network model based on dual channel convolution is proposed. For the hypergraph constructed from technological intellectual property data, the hypergraph channel and the line expanded graph channel of the hypergraph are used to learn the hypergraph, and the attention mechanism is introduced to adaptively fuse the output representations of the two channels. The proposed model outperforms the existing approaches on a variety of datasets.