EUVIMEDEUVIMED entdecken
Crossref

A Practical Survey on Faster and Lighter Transformers

Quentin Fournier, Gaétan Marceau Caron, Daniel Aloise

ACM Computing Surveys · 31.12.2023 · 55 (14s) · 1-40

DOI: 10.1145/3586074 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 17.07.2023. Verfasst von Quentin Fournier und 2 weiteren Autor:innen. Die Arbeit wurde bisher 132-mal zitiert (Crossref) und nennt 142 Literaturangaben. Gefördert von: Natural Sciences and Engineering Research Council of Canada (NSERC), Prompt, Ericsson, Ciena, and EfficiOS.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recurrent neural networks are effective models to process sequences. However, they are unable to learn long-term dependencies because of their inherent sequential nature. As a solution, Vaswani et al. introduced the Transformer, a model solely based on the attention mechanism that is able to relate any two positions of the input sequence, hence modelling arbitrary long dependencies. The Transformer has improved the state-of-the-art across numerous sequence modelling tasks. However, its effectiveness comes at the expense of a quadratic computational and memory complexity with respect to the sequence length, hindering its adoption. Fortunately, the deep learning community has always been interested in improving the models’ efficiency, leading to a plethora of solutions such as parameter sharing, pruning, mixed-precision, and knowledge distillation. Recently, researchers have directly addressed the Transformer’s limitation by designing lower-complexity alternatives such as the Longformer, Reformer, Linformer, and Performer. However, due to the wide range of solutions, it has become challenging for researchers and practitioners to determine which methods to apply in practice to meet the desired tradeoff between capacity, computation, and memory. This survey addresses this issue by investigating popular approaches to make Transformers faster and lighter and by providing a comprehensive explanation of the methods’ strengths, limitations, and underlying assumptions.

Förderung

  • Natural Sciences and Engineering Research Council of Canada (NSERC), Prompt, Ericsson, Ciena, and EfficiOS

Zitieren

APA

Fournier, Q., Caron, G. M., & Aloise, D. (2023). A Practical Survey on Faster and Lighter Transformers. ACM Computing Surveys, 55(14s), 1-40. https://doi.org/10.1145/3586074

Vancouver

Fournier Q, Caron GM, Aloise D. A Practical Survey on Faster and Lighter Transformers. ACM Computing Surveys. 2023;55(14s):1-40. doi:10.1145/3586074

BibTeX
@article{Fournier2023,
  author = {Fournier, Quentin and Caron, Gaétan Marceau and Aloise, Daniel},
  title = {A Practical Survey on Faster and Lighter Transformers},
  journal = {ACM Computing Surveys},
  year = {2023},
  volume = {55},
  number = {14s},
  pages = {1--40},
  doi = {10.1145/3586074}
}
Kostenlos starten →