Depth-Adaptive Transformer

Abstract

State of the art sequence-to-sequence models for large scale tasks perform a fixed number of computations for each input sequence regardless of whether it is easy or hard to process. In this paper, we train Transformer models which can make output predictions at different stages of the network and we investigate different ways to predict how much computation is required for a particular sequence. Unlike dynamic computation in Universal Transformers, which applies the same set of layers iteratively, we apply different layers at every step to adjust both the amount of computation as well as the model capacity. On IWSLT German-English translation our approach matches the accuracy of a well tuned baseline Transformer while using less than a quarter of the decoder layers.

Published as a conference paper at ICLR 2020

References in corpus (3)

• Universal Transformers
• Adaptive Computation Time for Recurrent Neural Networks
• Multi-Scale Dense Networks for Resource Efficient Image Classification

Cited by in corpus (7)

• Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
• Paradigm Shift in Natural Language Processing
• Dual-view Molecule Pre-training
• Cortex: A Compiler for Recursive Deep Learning Models
• Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search
• Current Limitations of Language Models: What You Need is Retrieval
• Depth-Adaptive Graph Recurrent Network for Text Classification