A Flexible Generative Framework for Graph-based Semi-supervised Learning

NeurIPS 2019  ·  Jiaqi Ma, Weijing Tang, Ji Zhu, Qiaozhu Mei ·

We consider a family of problems that are concerned about making predictions for the majority of unlabeled, graph-structured data samples based on a small proportion of labeled samples. Relational information among the data samples, often encoded in the graph/network structure, is shown to be helpful for these semi-supervised learning tasks. However, conventional graph-based regularization methods and recent graph neural networks do not fully leverage the interrelations between the features, the graph, and the labels. In this work, we propose a flexible generative framework for graph-based semi-supervised learning, which approaches the joint distribution of the node features, labels, and the graph structure. Borrowing insights from random graph models in network science literature, this joint distribution can be instantiated using various distribution families. For the inference of missing labels, we exploit recent advances of scalable variational inference techniques to approximate the Bayesian posterior. We conduct thorough experiments on benchmark datasets for graph-based semi-supervised learning. Results show that the proposed methods outperform the state-of-the-art models in most settings.

PDF Abstract NeurIPS 2019 PDF NeurIPS 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Node Classification Citeseer G3NN Accuracy 74.5% # 28
Training Split 20 per node with early stopping set # 1
Validation YES # 1
Node Classification CiteSeer with Public Split: fixed 20 nodes per class G3NN Accuracy 74.5% # 7
Node Classification Cora G3NN Accuracy 82.9% # 48
Training Split 20 per node with early stopping set # 1
Validation YES # 1
Node Classification Cora with Public Split: fixed 20 nodes per class G3NN Accuracy 82.9% # 22
Node Classification Pubmed G3NN Accuracy 78.4% # 55
Training Split 20 per node with early stopping set # 1
Validation YES # 1
Node Classification PubMed with Public Split: fixed 20 nodes per class G3NN Accuracy 78.4% # 25

Methods


No methods listed for this paper. Add relevant methods here