Robust Domain Generalisation by Enforcing Distribution Invariance

Abstract

Many conventional statistical machine learning algorithms generalise poorly if distribution bias exists in the datasets. For example, distribution bias arises in the context of domain generalisation, where knowledge acquired from multiple source domains need to be used in a previously unseen target domains. We propose Elliptical Summary Randomisation (ESRand), an efficient domain generalisation approach that comprises of a randomised kernel and elliptical data summarisation. ESR and learns a domain interdependent projection to a latent subspace that minimises the existing biases to the data while maintaining the functional relationship between domains. In the latent subspace, ellipsoidal sum..