Size-Invariant Graph Representations for Graph Classification Extrapolations
It addresses an underexplored challenge in graph representation learning for scenarios where test data distribution differs from training, which is incremental as it builds on existing methods.
The paper tackled the problem of out-of-distribution graph classification by using a causal model to learn invariant representations, showing improved extrapolation between train and test data in synthetic and real-world experiments.
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.