A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck

by   James Henderson, et al.
Idiap Research Institute

We propose a VAE for Transformers by developing a variational information bottleneck regulariser for Transformer embeddings. We formalise the embedding space of Transformer encoders as mixture probability distributions, and use Bayesian nonparametrics to derive a nonparametric variational information bottleneck (NVIB) for such attention-based embeddings. The variable number of mixture components supported by nonparametric methods captures the variable number of vectors supported by attention, and the exchangeability of our nonparametric distributions captures the permutation invariance of attention. This allows NVIB to regularise the number of vectors accessible with attention, as well as the amount of information in individual vectors. By regularising the cross-attention of a Transformer encoder-decoder with NVIB, we propose a nonparametric variational autoencoder (NVAE). Initial experiments on training a NVAE on natural language text show that the induced embedding space has the desired properties of a VAE for Transformers.


page 1

page 2

page 3

page 4


Transformer-based Conditional Variational Autoencoder for Controllable Story Generation

We investigate large-scale latent variable models (LVMs) for neural stor...

Regularizing Transformers With Deep Probabilistic Layers

Language models (LM) have grown with non-stop in the last decade, from s...

Multimodal Transformer for Parallel Concatenated Variational Autoencoders

In this paper, we propose a multimodal transformer using parallel concat...

On Isotropy Calibration of Transformers

Different studies of the embedding space of transformer models suggest t...

Finetuning Pretrained Transformers into Variational Autoencoders

Text variational autoencoders (VAEs) are notorious for posterior collaps...

Analyzing Transformer Dynamics as Movement through Embedding Space

Transformer language models exhibit intelligent behaviors such as unders...

Semi-supervised multiscale dual-encoding method for faulty traffic data detection

Inspired by the recent success of deep learning in multiscale informatio...

Please sign up or login with your details

Forgot password? Click here to reset