Should Graph Neural Networks Use Features, Edges, Or Both?
arXiv:2103.06857
Abstract
Graph Neural Networks (GNNs) are the first choice for learning algorithms on graph data. GNNs promise to integrate (i) node features as well as (ii) edge information in an end-to-end learning algorithm. How does this promise work out practically? In this paper, we study to what extend GNNs are necessary to solve prominent graph classification problems. We find that for graph classification, a GNN is not more than the sum of its parts. We also find that, unlike features, predictions with an edge-only model do not always transfer to GNNs.
References in corpus (10)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Neural Message Passing for Quantum Chemistry
- Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
- Pitfalls of Graph Neural Network Evaluation
- Open Graph Benchmark: Datasets for Machine Learning on Graphs
- TUDataset: A collection of benchmark datasets for learning with graphs
- Benchmarking Graph Neural Networks
- Towards Sparse Hierarchical Graph Classifiers
- Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
- Dimensional Reweighting Graph Convolutional Networks