A pipeline for fair comparison of graph neural networks in node classification tasks
arXiv:2012.10619
Abstract
Graph neural networks (GNNs) have been investigated for potential applicability in multiple fields that employ graph data. However, there are no standard training settings to ensure fair comparisons among new methods, including different model architectures and data augmentation techniques. We introduce a standard, reproducible benchmark to which the same training settings can be applied for node classification. For this benchmark, we constructed 9 datasets, including both small- and medium-scale datasets from different fields, and 7 different models. We design a k-fold model assessment strategy for small datasets and a standard set of model training procedures for all datasets, enabling a standard experimental pipeline for GNNs to help ensure fair model architecture comparisons. We use node2vec and Laplacian eigenvectors to perform data augmentation to investigate how input features affect the performance of the models. We find topological information is important for node classification tasks. Increasing the number of model layers does not improve the performance except on the PATTERN and CLUSTER datasets, in which the graphs are not connected. Data augmentation is highly useful, especially using node2vec in the baseline, resulting in a substantial baseline performance improvement.
arXiv comment18 pages, 10 figures
References in corpus (21)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
- Fast Graph Representation Learning with PyTorch Geometric
- DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
- Pitfalls of Graph Neural Network Evaluation
- Open Graph Benchmark: Datasets for Machine Learning on Graphs
- Graph Neural Networks with convolutional ARMA filters
- Gated Graph Sequence Neural Networks
- How Powerful are Graph Neural Networks?
- GraphSAINT: Graph Sampling Based Inductive Learning Method
- Residual Gated Graph ConvNets
- PairNorm: Tackling Oversmoothing in GNNs
- Benchmarking Graph Neural Networks
- An Efficient Graph Convolutional Network Technique for the Travelling Salesman Problem
- Towards Sparse Hierarchical Graph Classifiers
- A Two-Step Graph Convolutional Decoder for Molecule Generation
- Relational Pooling for Graph Representations
- Understanding and Resolving Performance Degradation in Graph Convolutional Networks