# Neural Attention: A Novel Mechanism for Enhanced Expressive Power in Transformer Models

arXiv: https://arxiv.org/abs/2502.17206 · HTML: https://mlsanity.com/paper/2502.17206/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 14 references that are in the map.
- First posted on arXiv 24 Feb 2025.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Pay Attention to MLPs](https://mlsanity.com/paper/2105.08050/) (2021)
- [SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications](https://mlsanity.com/paper/2303.15446/) (2023)
- [Fastformer: Additive Attention Can Be All You Need](https://mlsanity.com/paper/2108.09084/) (2021)
- [CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications](https://mlsanity.com/paper/2408.03703/) (2024)
- [Expanding Expressivity in Transformer Models with M"obiusAttention](https://mlsanity.com/paper/2409.12175/) (2024)
- [Efficient Context Propagating Perceiver Architectures for Auto-Regressive Language Modeling](https://mlsanity.com/paper/2412.06106/) (2024)

## Abstract (arXiv)

Transformer models typically calculate attention matrices using dot products, which have limitations when capturing nonlinear relationships between embedding vectors. We propose Neural Attention, a technique that replaces dot products with feed-forward networks, enabling a more expressive representation of relationships between tokens. This approach modifies only the attention matrix calculation while preserving the matrix dimensions, making it easily adaptable to existing transformer-based architectures. We provide a detailed mathematical justification for why Neural Attention increases representational capacity and conduct controlled experiments to validate this claim. When comparing Neural Attention and Dot-Product Attention, NLP experiments on WikiText-103 show a reduction in perplexity of over 2 percent. Similarly, experiments on CIFAR-10 and CIFAR-100 show improvements in accuracy of more than 4 percentage points for image classification tasks. While Neural Attention introduces higher computational demands, we develop techniques to mitigate these challenges, ensuring practical usability without sacrificing the increased expressivity it provides. This work establishes Neural Attention as an effective means of enhancing the predictive capabilities of transformer models across a variety of applications. The code for all experiments is available at https://github.com/awayfromzel/neural-attention-research.