English

EcoTransformer: Attention without Multiplication

Machine Learning 2025-08-07 v2 Artificial Intelligence Computation and Language

Abstract

The Transformer, with its scaled dot-product attention mechanism, has become a foundational architecture in modern AI. However, this mechanism is computationally intensive and incurs substantial energy costs. We propose a new Transformer architecture EcoTransformer, in which the output context vector is constructed as the convolution of the values using a Laplacian kernel, where the distances are measured by the L1 metric between the queries and keys. Compared to dot-product based attention, the new attention score calculation is free of matrix multiplication. It performs on par with, or even surpasses, scaled dot-product attention in NLP, bioinformatics, and vision tasks, while consuming significantly less energy. (This version (v2) supersedes v1 and reflects the intended release and licensing.)

Keywords

Cite

@article{arxiv.2507.20096,
  title  = {EcoTransformer: Attention without Multiplication},
  author = {Xin Gao and Xingming Xu and Shirin Amiraslani and Hong Xu},
  journal= {arXiv preprint arXiv:2507.20096},
  year   = {2025}
}

Comments

8 pages, 1 figure

R2 v1 2026-07-01T04:20:33.643Z