Deep Graph Neural Networks with Shallow Subgraph Samplers
Abstract
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. On the largest public graph dataset, ogbn-papers100M, we achieve state-of-the-art accuracy with an order of magnitude reduction in hardware cost.
Cite
@article{arxiv.2012.01380,
title = {Deep Graph Neural Networks with Shallow Subgraph Samplers},
author = {Hanqing Zeng and Muhan Zhang and Yinglong Xia and Ajitesh Srivastava and Andrey Malevich and Rajgopal Kannan and Viktor Prasanna and Long Jin and Ren Chen},
journal= {arXiv preprint arXiv:2012.01380},
year = {2022}
}
Comments
The complete version of this paper is accepted to NeurIPS 2021, available on arXiv under the new title "Decoupling the depth and scope of graph neural networks" (arXiv:2201.07858). This version, "Deep graph neural networks with shallow subgraph samplers", is a short version and we withdraw it to avoid confusion. Please always refer to arXiv:2201.07858