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.

Multilevel Monte-Carlo (MLMC) technique and establish its sample and computational complexities.

Unless stated otherwise we use American English for transcriptions.

Here the concept of Granger causality is employed to propose a new criterion for unsupervised learning that is appropriate in the case of temporally-dependent source signals. The basic idea is to identify two projections of a multivariate time series such that the Granger causality among the resulting pair of components is maximized.

For instance, patients' diagnosis varies substantially across medical centers but collaboratively form long-tailed distributions for