Scalable Graph Neural Networks for Heterogeneous Graphs

Abstract

Graph neural networks (GNNs) are a popular class of parametric model for learning over graph-structured data. Recent work has argued that GNNs primarily use the graph for feature smoothing, and have shown competitive results on benchmark tasks by simply operating on graph-smoothed node features, rather than using end-to-end learned feature hierarchies that are challenging to scale to large graphs. In this work, we ask whether these results can be extended to heterogeneous graphs, which encode multiple types of relationship between different entities. We propose Neighbor Averaging over Relation Subgraphs (NARS), which trains a classifier on neighbor-averaged features for randomly-sampled subgraphs of the "metagraph" of relations. We describe optimizations to allow these sets of node features to be computed in a memory-efficient way, both at training and inference time. NARS achieves a new state of the art accuracy on several benchmark datasets, outperforming more expensive GNN-based methods

References in corpus (14)

• Inductive Representation Learning on Large Graphs
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Simplifying Graph Convolutional Networks
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• How Powerful are Graph Neural Networks?
• GraphSAINT: Graph Sampling Based Inductive Learning Method
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• PyTorch-BigGraph: A Large-scale Graph Embedding System
• SIGN: Scalable Inception Graph Neural Networks
• Stochastic Training of Graph Convolutional Networks with Variance Reduction
• Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks
• Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification

Cited by in corpus (7)

• Graph Attention Multi-Layer Perceptron
• Multiplex Heterogeneous Graph Convolutional Network
• MECCH: Metapath Context Convolution-based Heterogeneous Graph Neural Networks
• Efficient Heterogeneous Graph Learning via Random Projection
• Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
• Large-scale graph representation learning with very deep GNNs and self-supervision
• Scalable Consistency Training for Graph Neural Networks via Self-Ensemble Self-Distillation