Depth-Wise Attention (DWAtt): A Layer Fusion Method for Data-Efficient Classification

arXiv:2209.15168v2 Announce Type: replace-cross
Abstract: Language Models pretrained on large textual data have been shown to encode different types of knowledge simultaneously. Traditionally, only the features from the last layer are used when adapting to new tasks or data. We put forward that, when using or finetuning deep pretrained models, intermediate layer features that may be relevant to the downstream task are buried too deep to be used efficiently in terms of needed samples or steps. To test this, we …

abstract arxiv attention classification cs.cl cs.lg data encode features finetuning fusion knowledge language language models layer pretrained models tasks textual type types wise