Building Blocks for a Complex-Valued Transformer Architecture

Abstract

Most deep learning pipelines are built on real-valued operations to deal with real-valued inputs such as images, speech or music signals. However, a lot of applications naturally make use of complex-valued signals or images, such as MRI or remote sensing. Additionally the Fourier transform of signals is complex-valued and has numerous applications. We aim to make deep learning directly applicable to these complex-valued signals without using projections into ℝ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> . Thus we add to the recent developments of complex-valued neural networks by presenting building blocks to transfer the transformer architecture to the complex domain. We present multiple versions of a complex-valued Scaled Dot-Product Attention mechanism as well as a complex-valued layer normalization. We test on a classification and a sequence generation task on the MusicNet dataset and show improved robustness to overfitting while maintaining on-par performance when compared to the real-valued transformer architecture.