# Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction

arXiv: https://arxiv.org/abs/1808.03867 · HTML: https://mlsanity.com/paper/1808.03867/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2018.

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

- [ProtoTEx: Explaining Model Decisions with Prototype Tensors](https://mlsanity.com/paper/2204.05426/) (2022)
- [Predicting Customer Lifetime Value in Free-to-Play Games](https://mlsanity.com/paper/2209.12619/) (2022)
- [Reduced Order Probabilistic Emulation for Physics-Based Thermosphere Models](https://mlsanity.com/paper/2211.04392/) (2022)
- [Optimal Kernel Tuning Parameter Prediction using Deep Sequence Models](https://mlsanity.com/paper/2404.10162/) (2024)

## Abstract (arXiv)

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore pervasive throughout the network. Our model yields excellent results, outperforming state-of-the-art encoder-decoder systems, while being conceptually simpler and having fewer parameters.