Graph Convolutional Networks for Classification with a Structured Label Space

Abstract

It is a usual practice to ignore any structural information underlying classes in multi-class classification. In this paper, we propose a graph convolutional network (GCN) augmented neural network classifier to exploit a known, underlying graph structure of labels. The proposed approach resembles an (approximate) inference procedure in, for instance, a conditional random field (CRF). We evaluate the proposed approach on document classification and object recognition and report both accuracies and graph-theoretic metrics that correspond to the consistency of the model's prediction. The experiment results reveal that the proposed model outperforms a baseline method which ignores the graph structures of a label space in terms of graph-theoretic metrics.

References in corpus (4)

• Semi-Supervised Classification with Graph Convolutional Networks
• Fully Connected Deep Structured Networks
• Tying Word Vectors and Word Classifiers: A Loss Framework for Language Modeling
• Emergent Communication in a Multi-Modal, Multi-Step Referential Game

Cited by in corpus (6)

• Learning Graph Neural Networks with Positive and Unlabeled Nodes
• Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks
• Attentional Multilabel Learning over Graphs: A Message Passing Approach
• Semi-Supervised Learning on Graphs Based on Local Label Distributions
• PK-GCN: Prior Knowledge Assisted Image Classification using Graph Convolution Networks
• Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs