## Learning Disentangled Representations with Invertible(Flow-based) Interpretation Networks

What are disentangled representations? How can we learn disentangled representations for any arbitrary model using flow-based generative models? Fig. 1: The IIN network can be applied to arbitrary existing models. IIN takes the representation z, learned by the arbitrary model and factorised it into smaller factors such that each factor learns to represent one generative … Read more