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

Abstract

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.

arXiv commentNeurIPS 2019

References in corpus (10)

• Efficient Estimation of Word Representations in Vector Space
• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Semi-Supervised Learning with Deep Generative Models
• Fast Graph Representation Learning with PyTorch Geometric
• Variational Graph Auto-Encoders
• MolGAN: An implicit generative model for small molecular graphs
• Revisiting Semi-Supervised Learning with Graph Embeddings
• Bayesian graph convolutional neural networks for semi-supervised classification
• Bayesian Semi-supervised Learning with Graph Gaussian Processes

Cited by in corpus (7)

• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• Graph Random Neural Network for Semi-Supervised Learning on Graphs
• Semi-Supervised Node Classification by Graph Convolutional Networks and Extracted Side Information
• CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks
• Uncertainty Propagation in Node Classification
• Heuristic Semi-Supervised Learning for Graph Generation Inspired by Electoral College
• Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and Clustering