Relative Positional Encoding for Transformers with Linear Complexity - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2021

Relative Positional Encoding for Transformers with Linear Complexity

Abstract

Recent advances in Transformer models allow for unprecedented sequence lengths, due to linear space and time complexity. In the meantime, relative positional encoding (RPE) was proposed as beneficial for classical Transformers and consists in exploiting lags instead of absolute positions for inference. Still, RPE is not available for the recent linear-variants of the Transformer, because it requires the explicit computation of the attention matrix, which is precisely what is avoided by such methods. In this paper, we bridge this gap and present Stochastic Positional Encoding as a way to generate PE that can be used as a replacement to the classical additive (sinusoidal) PE and provably behaves like RPE. The main theoretical contribution is to make a connection between positional encoding and cross-covariance structures of correlated Gaussian processes. We illustrate the performance of our approach on the Long-Range Arena benchmark and on music generation.
Fichier principal
Vignette du fichier
spe.pdf (7.12 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03256451 , version 1 (10-06-2021)

Identifiers

Cite

Antoine Liutkus, Ondřej Cífka, Shih-Lun Wu, Umut Şimşekli, Yi-Hsuan Yang, et al.. Relative Positional Encoding for Transformers with Linear Complexity. ICML 2021 - 38th International Conference on Machine Learning, Jul 2021, Virtual Only, United States. pp.7067-7079. ⟨hal-03256451⟩
1607 View
699 Download

Altmetric

Share

Gmail Facebook X LinkedIn More