DeepAI AI Chat
Log In Sign Up

Towards a Taxonomy of Graph Learning Datasets

by   Renming Liu, et al.
Montréal Institute of Learning Algorithms
Michigan State University

Graph neural networks (GNNs) have attracted much attention due to their ability to leverage the intrinsic geometries of the underlying data. Although many different types of GNN models have been developed, with many benchmarking procedures to demonstrate the superiority of one GNN model over the others, there is a lack of systematic understanding of the underlying benchmarking datasets, and what aspects of the model are being tested. Here, we provide a principled approach to taxonomize graph benchmarking datasets by carefully designing a collection of graph perturbations to probe the essential data characteristics that GNN models leverage to perform predictions. Our data-driven taxonomization of graph datasets provides a new understanding of critical dataset characteristics that will enable better model evaluation and the development of more specialized GNN models.


page 3

page 4


Taxonomy of Benchmarks in Graph Representation Learning

Graph Neural Networks (GNNs) extend the success of neural networks to gr...

Benchmarking Graph Neural Networks for Internet Routing Data

The Internet is composed of networks, called Autonomous Systems (or, ASe...

GraphWorld: Fake Graphs Bring Real Insights for GNNs

Despite advances in the field of Graph Neural Networks (GNNs), only a sm...

Pitfalls of Graph Neural Network Evaluation

Semi-supervised node classification in graphs is a fundamental problem i...

Benchmarking Graph Neural Networks

Graph neural networks (GNNs) have become the standard toolkit for analyz...

ProGNNosis: A Data-driven Model to Predict GNN Computation Time Using Graph Metrics

Graph Neural Networks (GNN) show great promise in problems dealing with ...

Rethinking Graph Lottery Tickets: Graph Sparsity Matters

Lottery Ticket Hypothesis (LTH) claims the existence of a winning ticket...