In supervised learning, the question of data quality and curation has been overshadowed in recent years by increasingly more powerful and expressive models that can ingest internet-scale data.

Molecular representation learning lays the foundation for drug discovery. However, existing methods suffer from poor out-of-distribution (OOD) generalization, particularly when data for training and testing originate from different environments.

"Effective robustness" measures the extra out-of-distribution (OOD) robustness

However, sampling is not the only source of uncertainty. In practice, distributions change between locations and across time.

Work done during an internship at Tencent AI Lab.

Distributional shifts pose a significant challenge to achieving robustness in contemporary machine learning.

We use the iWildCam version 2.0 released in 2021 as a Examples of train set images can be seen in Figure 14. Random examples from the out-of-distribution test set. Figure 15 shows examples of train set images. Figure 15: Random examples from the ImageNet ILSVRC 2012 challenge train set [37, 11]. The full training set is notably not class balanced, exhibiting a long-tailed distribution (see Figure 16). Figure 17: Random examples from the iNaturalist 2017 challenge train set [46].