# Should Graph Neural Networks Use Features, Edges, Or Both?

@article{Faber2021ShouldGN, title={Should Graph Neural Networks Use Features, Edges, Or Both?}, author={Lukas Faber and Yifan Lu and Roger Wattenhofer}, journal={ArXiv}, year={2021}, volume={abs/2103.06857} }

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… Expand

#### One Citation

#### References

SHOWING 1-10 OF 31 REFERENCES

Pitfalls of Graph Neural Network Evaluation

- Computer Science, Mathematics
- ArXiv
- 2018

Hierarchical Graph Representation Learning with Differentiable Pooling

- Computer Science, Mathematics
- NeurIPS
- 2018

Generalization and Representational Limits of Graph Neural Networks

- Computer Science, Mathematics
- ICML
- 2020

Combining Label Propagation and Simple Models Out-performs Graph Neural Networks

- Computer Science
- ArXiv
- 2020

Representation Learning on Graphs with Jumping Knowledge Networks

- Computer Science, Mathematics
- ICML
- 2018

Semi-Supervised Classification with Graph Convolutional Networks

- Computer Science, Mathematics
- ICLR
- 2017

A Comprehensive Survey on Graph Neural Networks

- Computer Science, Mathematics
- IEEE Transactions on Neural Networks and Learning Systems
- 2019