Size-Invariant Graph Representations for Graph Classification Extrapolations
Size-Invariant Graph Representations for Graph Classification Extrapolations
复制标题
DOI：
--
复制
发表时间：
2021-03
期刊：
影响因子：
--
通讯作者：
Beatrice Bevilacqua;Yangze Zhou;Bruno Ribeiro
中科院分区：
文献类型：
--
作者：
Beatrice Bevilacqua;Yangze Zhou;Bruno Ribeiro
一般而言，图表示学习方法假设训练数据和测试数据来自相同的分布。在这项工作中，我们考虑了图表示学习领域中一个未被探索的领域：分布外(OOD)图分类任务，其中训练数据和测试数据具有不同的分布，测试数据在训练期间不可用。我们的工作表明，可以使用因果模型来学习近似不变表示，以便更好地在训练数据和测试数据之间进行外推。最后，我们以合成和真实世界的数据集实验结束，展示了不随训练/测试分布偏移而变化的表示的好处。
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.