# Efficient Attention using a Fixed-Size Memory Representation

arXiv: https://arxiv.org/abs/1707.00110 · HTML: https://mlsanity.com/paper/1707.00110/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jul 2017.

## Built on by (most cited first, 4 of 4)

- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [LambdaNetworks: Modeling Long-Range Interactions Without Attention](https://mlsanity.com/paper/2102.08602/) (2021)
- [LSG Attention: Extrapolation of pretrained Transformers to long sequences](https://mlsanity.com/paper/2210.15497/) (2022)
- [Iterated Piecewise Affine (IPA) Approximation for Language Modeling](https://mlsanity.com/paper/2306.12317/) (2023)

## Abstract (arXiv)

The standard content-based attention mechanism typically used in sequence-to-sequence models is computationally expensive as it requires the comparison of large encoder and decoder states at each time step. In this work, we propose an alternative attention mechanism based on a fixed size memory representation that is more efficient. Our technique predicts a compact set of K attention contexts during encoding and lets the decoder compute an efficient lookup that does not need to consult the memory. We show that our approach performs on-par with the standard attention mechanism while yielding inference speedups of 20% for real-world translation tasks and more for tasks with longer sequences. By visualizing attention scores we demonstrate that our models learn distinct, meaningful alignments.