On Graph Classification Networks, Datasets and Baselines
arXiv:1905.04682
Abstract
Graph classification receives a great deal of attention from the non-Euclidean machine learning community. Recent advances in graph coarsening have enabled the training of deeper networks and produced new state-of-the-art results in many benchmark tasks. We examine how these architectures train and find that performance is highly-sensitive to initialisation and depends strongly on jumping-knowledge structures. We then show that, despite the great complexity of these models, competitive performance is achieved by the simplest of models -- structure-blind MLP, single-layer GCN and fixed-weight GCN -- and propose these be included as baselines in future.
Submitted to the ICML 2019 Workshop on Learning and Reasoning with Graph-Structured Data
References in corpus (7)
- Inductive Representation Learning on Large Graphs
- Neural Message Passing for Quantum Chemistry
- Geometric deep learning: going beyond Euclidean data
- Fast Graph Representation Learning with PyTorch Geometric
- Hierarchical Graph Representation Learning with Differentiable Pooling
- Learning Convolutional Neural Networks for Graphs
- All you need is a good init
Cited by in corpus (7)
- Benchmarking Graph Neural Networks
- Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
- GraphWorld: Fake Graphs Bring Real Insights for GNNs
- Supervised Learning on Relational Databases with Graph Neural Networks
- GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersection
- Lymph Node Graph Neural Networks for Cancer Metastasis Prediction
- Learning distributed representations of graphs with Geo2DR