On the Transferability of VAE Embeddings using Relational Knowledge with Semi-Supervision

11/13/2020
by   Harald Strömfelt, et al.
6

We propose a new model for relational VAE semi-supervision capable of balancing disentanglement and low complexity modelling of relations with different symbolic properties. We compare the relative benefits of relation-decoder complexity and latent space structure on both inductive and transductive transfer learning. Our results depict a complex picture where enforcing structure on semi-supervised representations can greatly improve zero-shot transductive transfer, but may be less favourable or even impact negatively the capacity for inductive transfer.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset