Graph Partition Neural Networks for Semi-Supervised Classification

Abstract

We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs. GPNNs alternate between locally propagating information between nodes in small subgraphs and globally propagating information between the subgraphs. To efficiently partition graphs, we experiment with several partitioning algorithms and also propose a novel variant for fast processing of large scale graphs. We extensively test our model on a variety of semi-supervised node classification tasks. Experimental results indicate that GPNNs are either superior or comparable to state-of-the-art methods on a wide variety of datasets for graph-based semi-supervised classification. We also show that GPNNs can achieve similar performance as standard GNNs with fewer propagation steps.

References in corpus (4)

• Few-Shot Learning with Graph Neural Networks
• Residual Belief Propagation: Informed Scheduling for Asynchronous Message Passing
• Improved Dynamic Schedules for Belief Propagation
• Situation Recognition with Graph Neural Networks

Cited by in corpus (16)

• Structured Neural Summarization
• Graph Neural Networks: Taxonomy, Advances and Trends
• Graph HyperNetworks for Neural Architecture Search
• Batch Virtual Adversarial Training for Graph Convolutional Networks
• PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm
• Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
• Label Efficient Semi-Supervised Learning via Graph Filtering
• Large-scale graph representation learning with very deep GNNs and self-supervision
• Neural Graph Embedding Methods for Natural Language Processing
• Learning a Static Bug Finder from Data
• GraphTheta: A Distributed Graph Neural Network Learning System With Flexible Training Strategy
• Meta-path Free Semi-supervised Learning for Heterogeneous Networks
• gSuite: A Flexible and Framework Independent Benchmark Suite for Graph Neural Network Inference on GPUs
• DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition
• Deep Dive into Semi-Supervised ELBO for Improving Classification Performance
• Lovasz Convolutional Networks