Skip to yearly menu bar Skip to main content


Learning Generative Models across Incomparable Spaces

Charlotte Bunne · David Alvarez-Melis · Andreas Krause · Stefanie Jegelka

Pacific Ballroom #173

Keywords: [ Representation Learning ] [ Networks and Relational Learning ] [ Generative Adversarial Networks ] [ Dimensionality Reduction ]


Generative Adversarial Networks have shown remarkable success in learning a distribution that faithfully recovers a reference distribution in its entirety. However, in some cases, we may want to only learn some aspects (e.g., cluster or manifold structure), while modifying others (e.g., style, orientation or dimension). In this work, we propose an approach to learn generative models across such incomparable spaces, and demonstrate how to steer the learned distribution towards target properties. A key component of our model is the Gromov-Wasserstein distance, a notion of discrepancy that compares distributions relationally rather than absolutely. While this framework subsumes current generative models in identically reproducing distributions, its inherent flexibility allows application to tasks in manifold learning, relational learning and cross-domain learning.

Live content is unavailable. Log in and register to view live content