Benchmarking Graph Neural Networks

by   Vijay Prakash Dwivedi, et al.

Graph neural networks (GNNs) have become the standard toolkit for analyzing and learning from data on graphs. They have been successfully applied to a myriad of domains including chemistry, physics, social sciences, knowledge graphs, recommendation, and neuroscience. As the field grows, it becomes critical to identify the architectures and key mechanisms which generalize across graphs sizes, enabling us to tackle larger, more complex datasets and domains. Unfortunately, it has been increasingly difficult to gauge the effectiveness of new GNNs and compare models in the absence of a standardized benchmark with consistent experimental settings and large datasets. In this paper, we propose a reproducible GNN benchmarking framework, with the facility for researchers to add new datasets and models conveniently. We apply this benchmarking framework to novel medium-scale graph datasets from mathematical modeling, computer vision, chemistry and combinatorial problems to establish key operations when designing effective GNNs. Precisely, graph convolutions, anisotropic diffusion, residual connections and normalization layers are universal building blocks for developing robust and scalable GNNs.


Learning Graph Algorithms With Recurrent Graph Neural Networks

Classical graph algorithms work well for combinatorial problems that can...

Training Graph Neural Networks on Growing Stochastic Graphs

Graph Neural Networks (GNNs) rely on graph convolutions to exploit meani...

Hierarchical GNNs for Large Graph Generation

Large graphs are present in a variety of domains, including social netwo...

Bag of Tricks for Training Deeper Graph Neural Networks: A Comprehensive Benchmark Study

Training deep graph neural networks (GNNs) is notoriously hard. Besides ...

Towards a Taxonomy of Graph Learning Datasets

Graph neural networks (GNNs) have attracted much attention due to their ...

Search for the UGLE Truth: An Investigation into Unsupervised GNN Learning Environments

Graph Neural Networks (GNNs) are a pertinent tool for any machine learni...

Code Repositories


Repository for benchmarking graph neural networks

view repo


GatedGCN Pattern Dataset Example

view repo


Working repo for studying aggregation functions in GNNs

view repo


Supplementary codes for NeurIPS 2021 submission 1423: Permutation-sensitive Neural Networks Express More on Graph

view repo

Please sign up or login with your details

Forgot password? Click here to reset