Size-Invariant Graph Representations for Graph Classification Extrapolations
Abstract
In general, graph representation learning methods assume that the train and test data come from the same distribution. In this work we consider an underexplored area of an otherwise rapidly developing field of graph representation learning: The task of out-of-distribution (OOD) graph classification, where train and test data have different distributions, with test data unavailable during training. Our work shows it is possible to use a causal model to learn approximately invariant representations that better extrapolate between train and test data. Finally, we conclude with synthetic and real-world dataset experiments showcasing the benefits of representations that are invariant to train/test distribution shifts.
Cite
Text
Bevilacqua et al. "Size-Invariant Graph Representations for Graph Classification Extrapolations." International Conference on Machine Learning, 2021.Markdown
[Bevilacqua et al. "Size-Invariant Graph Representations for Graph Classification Extrapolations." International Conference on Machine Learning, 2021.](https://mlanthology.org/icml/2021/bevilacqua2021icml-sizeinvariant/)BibTeX
@inproceedings{bevilacqua2021icml-sizeinvariant,
title = {{Size-Invariant Graph Representations for Graph Classification Extrapolations}},
author = {Bevilacqua, Beatrice and Zhou, Yangze and Ribeiro, Bruno},
booktitle = {International Conference on Machine Learning},
year = {2021},
pages = {837-851},
volume = {139},
url = {https://mlanthology.org/icml/2021/bevilacqua2021icml-sizeinvariant/}
}