Litcius/Paper detail

Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification

Fangyuan Lei, Xun Liu, Zhengming Li, Qingyun Dai, Senhong Wang

2021Mathematical Problems in Engineering18 citationsDOIOpen Access PDF

Abstract

Graph convolutional network (GCN) is an efficient network for learning graph representations. However, it costs expensive to learn the high-order interaction relationships of the node neighbor. In this paper, we propose a novel graph convolutional model to learn and fuse multihop neighbor information relationships. We adopt the weight-sharing mechanism to design different order graph convolutions for avoiding the potential concerns of overfitting. Moreover, we design a new multihop neighbor information fusion (MIF) operator which mixes different neighbor features from 1-hop to k-hops. We theoretically analyse the computational complexity and the number of trainable parameters of our models. Experiment on text networks shows that the proposed models achieve state-of-the-art performance than the text GCN.

Topics & Concepts

OverfittingComputer scienceGraphk-nearest neighbors algorithmTheoretical computer scienceArtificial intelligenceArtificial neural networkAdvanced Graph Neural NetworksText and Document Classification TechnologiesComplex Network Analysis Techniques
Multihop Neighbor Information Fusion Graph Convolutional Network for Text Classification | Litcius