Log In Sign Up

Scaling Up Graph Neural Networks Via Graph Coarsening

by   Zengfeng Huang, et al.

Scalability of graph neural networks remains one of the major challenges in graph machine learning. Since the representation of a node is computed by recursively aggregating and transforming representation vectors of its neighboring nodes from previous layers, the receptive fields grow exponentially, which makes standard stochastic optimization techniques ineffective. Various approaches have been proposed to alleviate this issue, e.g., sampling-based methods and techniques based on pre-computation of graph filters. In this paper, we take a different approach and propose to use graph coarsening for scalable training of GNNs, which is generic, extremely simple and has sublinear memory and time costs during training. We present extensive theoretical analysis on the effect of using coarsening operations and provides useful guidance on the choice of coarsening methods. Interestingly, our theoretical analysis shows that coarsening can also be considered as a type of regularization and may improve the generalization. Finally, empirical results on real world datasets show that, simply applying off-the-shelf coarsening methods, we can reduce the number of nodes by up to a factor of ten without causing a noticeable downgrade in classification accuracy.


Neighborhood Enlargement in Graph Neural Networks

Graph Neural Network (GNN) is an effective framework for representation ...

When Does A Spectral Graph Neural Network Fail in Node Classification?

Spectral Graph Neural Networks (GNNs) with various graph filters have re...

Going Deeper into Permutation-Sensitive Graph Neural Networks

The invariance to permutations of the adjacency matrix, i.e., graph isom...

Scaling up graph homomorphism for classification via sampling

Feature generation is an open topic of investigation in graph machine le...

FairGNN: Eliminating the Discrimination in Graph Neural Networks with Limited Sensitive Attribute Information

Graph neural networks (GNNs) have shown great power in modeling graph st...

GeniePath: Graph Neural Networks with Adaptive Receptive Paths

We present, GeniePath, a scalable approach for learning adaptive recepti...

Code Repositories


Code for the KDD 2021 paper "Scaling Up Graph Neural Networks Via Graph Coarsening"

view repo