Nonparametric Variational Regularisation of Pretrained Transformers

摘要

Pretrained transformers have demonstrated impressive abilities, but tend not to generalise well out-of-domain and are very expensive to fine-tune on new domain data. Nonparametric Variational Information Bottleneck (NVIB) has been proposed as a regulariser for training cross-attention in transformers, potentially addressing this domain overfitting problem. We extend the NVIB framework to replace all types of attention functions in transformers. We show that existing pretrained transformers can be reinterpreted as nonparametric variational models using an empirical prior distribution and identity initialisation with controllable hyperparameters. We then show that changing the initialisation introduces a novel, information-theoretic post-training regularisation in the attention mechanism, which improves out-of-domain generalisation on NLP tasks without any additional training. This success supports the hypothesis that the way pretrained transformer embeddings represent information is accurately characterised by nonparametric variational Bayesian models.