Deep Graph Neural Networks with Shallow Subgraph Samplers

by   Hanqing Zeng, et al.

While Graph Neural Networks (GNNs) are powerful models for learning representations on graphs, most state-of-the-art models do not have significant accuracy gain beyond two to three layers. Deep GNNs fundamentally need to address: 1). expressivity challenge due to oversmoothing, and 2). computation challenge due to neighborhood explosion. We propose a simple "deep GNN, shallow sampler" design principle to improve both the GNN accuracy and efficiency – to generate representation of a target node, we use a deep GNN to pass messages only within a shallow, localized subgraph. A properly sampled subgraph may exclude irrelevant or even noisy nodes, and still preserve the critical neighbor features and graph structures. The deep GNN then smooths the informative local signals to enhance feature learning, rather than oversmoothing the global graph signals into just "white noise". We theoretically justify why the combination of deep GNNs with shallow samplers yields the best learning performance. We then propose various sampling algorithms and neural architecture extensions to achieve good empirical results. Experiments on five large graphs show that our models achieve significantly higher accuracy and efficiency, compared with state-of-the-art.



There are no comments yet.


page 1

page 2

page 3

page 4


Decoupling the Depth and Scope of Graph Neural Networks

State-of-the-art Graph Neural Networks (GNNs) have limited scalability w...

Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs

Graph Neural Networks (GNNs) are emerging machine learning models on gra...

Measuring and Sampling: A Metric-guided Subgraph Learning Framework for Graph Neural Network

Graph neural network (GNN) has shown convincing performance in learning ...

SEA: Graph Shell Attention in Graph Neural Networks

A common issue in Graph Neural Networks (GNNs) is known as over-smoothin...

GraphCrop: Subgraph Cropping for Graph Classification

We present a new method to regularize graph neural networks (GNNs) for b...

Accurate, Efficient and Scalable Training of Graph Neural Networks

Graph Neural Networks (GNNs) are powerful deep learning models to genera...

Continuous-Depth Neural Models for Dynamic Graph Prediction

We introduce the framework of continuous-depth graph neural networks (GN...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.