Research Area:  Machine Learning

Abstract:

Effectively scaling large Transformer models is a main driver of recent advances in natural language processing. Dynamic neural networks, as an emerging research direction, are capable of scaling up neural networks with sub-linear increases in computation and time by dynamically adjusting their computational path based on the input. Dynamic neural networks could be a promising solution to the growing parameter numbers of pretrained language models, allowing both model pretraining with trillions of parameters and faster inference on mobile devices. In this survey, we summarize progress of three types of dynamic neural networks in NLP: skimming, mixture of experts, and early exit. We also highlight current challenges in dynamic neural networks and directions for future research.

Keywords:  
Dynamic Neural Networks
Natural Language Processing
Deep Learning
Machine Learning

Author(s) Name:  Canwen Xu, and Julian McAuley

Publisher name:  arXiv-CS

DOI:  arXiv:2202.07101

Volume Information:  arXiv:2202.07101

Paper Link:   https://arxiv.org/abs/2202.07101