Comparison of statistical distances can also enable distribution testing, quantification of distribution shifts, and provide methods to correct for distribution shift through domainadaptation[12]. Optimal transport theory provides a rich set of tools for comparing distributions inWasserstein Distance.

However, the generating process can be different in several aspects, such as the conditions and devices used for acquisition, different pre-processing, different compressions, etc. Domain adaptation

We propose Any2Graph, a generic framework for end-to-end Supervised Graph Prediction (SGP) i.e. a deep learning model that predicts an entire graph for any kind of input.

Among them, over-sampling and data augmentation aim to balance the data distribution by oversampling or generating closely related minority classes.

Neural Information Processing Systems http://nips.cc/