Timezone: »

 
Oral
Size-Invariant Graph Representations for Graph Classification Extrapolations
Beatrice Bevilacqua · Yangze Zhou · Bruno Ribeiro

Tue Jul 20 05:00 AM -- 05:20 AM (PDT) @ None

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.

Author Information

Beatrice Bevilacqua (Purdue University)
Yangze Zhou (Purdue University)
Bruno Ribeiro (Purdue University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors