## GMNN

swMATH ID: | 44770 |

Software Authors: | Meng Qu, Yoshua Bengio, Jian Tang |

Description: | GMNN: Graph Markov Neural Networks. 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. |

Homepage: | https://arxiv.org/abs/1905.06214 |

Source Code: | https://github.com/DeepGraphLearning/GMNN |

Dependencies: | Python |

Related Software: | NetKit; struc2vec; DeepWalk; GraphVAE; NetGAN; GraphRNN; MolGAN; node2vec; PyTorch; PMTK; SIGN; PairNorm; Tuffy; Tensor2Tensor; FP2VEC; FastGCN; Graclus; BRENDA; kLog; AFGen |

Cited in: | 6 Documents |

all
top 5

### Cited by 12 Authors

all
top 5

### Cited in 6 Serials

### Cited in 4 Fields

6 | Computer science (68-XX) |

3 | Statistics (62-XX) |

1 | Combinatorics (05-XX) |

1 | Game theory, economics, finance, and other social and behavioral sciences (91-XX) |