# DARTFormer: Finding The Best Type Of Attention

arXiv: https://arxiv.org/abs/2210.00641 · HTML: https://mlsanity.com/paper/2210.00641/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 25 references that are in the map.
- First posted on arXiv 2 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Generating Long Sequences with Sparse Transformers](https://mlsanity.com/paper/1904.10509/) (2019)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Efficient Transformers: A Survey](https://mlsanity.com/paper/2009.06732/) (2020)
- [Long Range Arena: A Benchmark for Efficient Transformers](https://mlsanity.com/paper/2011.04006/) (2020)
- [Generating Wikipedia by Summarizing Long Sequences](https://mlsanity.com/paper/1801.10198/) (2018)
- [PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search](https://mlsanity.com/paper/1907.05737/) (2019)
- [Sparse Sinkhorn Attention](https://mlsanity.com/paper/2002.11296/) (2020)
- [cosFormer: Rethinking Softmax in Attention](https://mlsanity.com/paper/2202.08791/) (2022)
- [Synthesizer: Rethinking Self-Attention in Transformer Models](https://mlsanity.com/paper/2005.00743/) (2020)
- [Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks](https://mlsanity.com/paper/1810.00825/) (2018)
- [Rethinking Architecture Selection in Differentiable NAS](https://mlsanity.com/paper/2108.04392/) (2021)
- [Neural Architecture Search on Efficient Transformers and Beyond](https://mlsanity.com/paper/2207.13955/) (2022)
- [RankNAS: Efficient Neural Architecture Search by Pairwise Ranking](https://mlsanity.com/paper/2109.07383/) (2021)
- [Finding Fast Transformers: One-Shot Neural Architecture Search by Component Composition](https://mlsanity.com/paper/2008.06808/) (2020)

## Built on by (most cited first, 3 of 3)

- [MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous Attention](https://mlsanity.com/paper/2211.13955/) (2022)
- [SlowFormer: Universal Adversarial Patch for Attack on Compute and Energy Efficiency of Inference Efficient Vision Transformers](https://mlsanity.com/paper/2310.02544/) (2023)
- [MIDAS: Mosaic Input-Specific Differentiable Architecture Search](https://mlsanity.com/paper/2602.17700/) (2026)

## Abstract (arXiv)

Given the wide and ever growing range of different efficient Transformer attention mechanisms, it is important to identify which attention is most effective when given a task. In this work, we are also interested in combining different attention types to build heterogeneous Transformers. We first propose a DARTS-like Neural Architecture Search (NAS) method to find the best attention for a given task, in this setup, all heads use the same attention (homogeneous models). Our results suggest that NAS is highly effective on this task, and it identifies the best attention mechanisms for IMDb byte level text classification and Listops. We then extend our framework to search for and build Transformers with multiple different attention types, and call them heterogeneous Transformers. We show that whilst these heterogeneous Transformers are better than the average homogeneous models, they cannot outperform the best. We explore the reasons why heterogeneous attention makes sense, and why it ultimately fails.