GMNN: Graph Markov Neural Networks
This addresses a fundamental problem in relational data modeling for applications like social network analysis or recommendation systems, offering an incremental improvement by integrating existing methods.
The paper tackles semi-supervised object classification in relational data by proposing Graph Markov Neural Networks (GMNN), which combine conditional random fields and graph neural networks to model label dependencies and learn representations, achieving state-of-the-art results in experiments on object classification, link classification, and unsupervised node representation learning.
This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutional networks). Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end training. In this paper, we propose the Graph Markov Neural Network (GMNN) that combines the advantages of both worlds. A GMNN models the joint distribution of object labels with a conditional random field, which can be effectively trained with the variational EM algorithm. In the E-step, one graph neural network learns effective object representations for approximating the posterior distributions of object labels. In the M-step, another graph neural network is used to model the local label dependency. Experiments on object classification, link classification, and unsupervised node representation learning show that GMNN achieves state-of-the-art results.