A Variational AutoEncoder for Transformers with Nonparametric Variational Information Bottleneck
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.
Code (0)
등록된 구현이 없습니다.
Tasks
DecoderMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Nonparametric Variational Regularisation of Pretrained Transformers
The current paradigm of large-scale pre-training and fine-tuning Transformer large language models has lead to significant improvements across the board in natural language processing. However, such large models are susc…
Stick-Breaking Variational Autoencoders
We extend Stochastic Gradient Variational Bayes to perform posterior inference for the weights of Stick-Breaking processes. This development allows us to define a Stick-Breaking Variational Autoencoder (SB-VAE), a Bayesi…
Streaming Adaptive Nonparametric Variational Autoencoder
We develop a data driven approach to perform clustering and end-to-end feature learning simultaneously for streaming data that can adaptively detect novel clusters in emerging data. Our approach, Adaptive Nonparametric V…
ClusteringFeature EngineeringVariational InferenceNonparametric Variational Auto-encoders for Hierarchical Representation Learning
The recently developed variational autoencoders (VAEs) have proved to be an effective confluence of the rich representational power of neural networks with Bayesian methods. However, most work on VAEs use a rather simple…
ClusteringRepresentation LearningVariational InferenceAdversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks
Variational Autoencoders (VAEs) are expressive latent variable models that can be used to learn complex probability distributions from training data. However, the quality of the resulting model crucially relies on the ex…