An Efficient Transformer Decoder with Compressed Sub-layers

by   Yanyang Li, et al.

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic formulation of the decoder, we show that under some mild conditions, the architecture could be simplified by compressing its sub-layers, the basic building block of Transformer, and achieves a higher parallelism. We thereby propose Compressed Attention Network, whose decoder layer consists of only one sub-layer instead of three. Extensive experiments on 14 WMT machine translation tasks show that our model is 1.42x faster with performance on par with a strong baseline. This strong baseline is already 2x faster than the widely used standard baseline without loss in performance.


Accelerating Neural Transformer via an Average Attention Network

With parallelizable attention networks, the neural Transformer is very f...

GTrans: Grouping and Fusing Transformer Layers for Neural Machine Translation

Transformer structure, stacked by a sequence of encoder and decoder netw...

EdgeFormer: A Parameter-Efficient Transformer for On-Device Seq2seq Generation

We propose EdgeFormer – a parameter-efficient Transformer of the encoder...

On the Sub-Layer Functionalities of Transformer Decoder

There have been significant efforts to interpret the encoder of Transfor...

Analyzing Word Translation of Transformer Layers

The Transformer translation model is popular for its effective paralleli...

Nana-HDR: A Non-attentive Non-autoregressive Hybrid Model for TTS

This paper presents Nana-HDR, a new non-attentive non-autoregressive mod...

Vision Transformer with Convolutional Encoder-Decoder for Hand Gesture Recognition using 24 GHz Doppler Radar

Transformers combined with convolutional encoders have been recently use...