# Delta Keyword Transformer: Bringing Transformers to the Edge through Dynamically Pruned Multi-Head Self-Attention

arXiv: https://arxiv.org/abs/2204.03479 · HTML: https://mlsanity.com/paper/2204.03479/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 37 references that are in the map.
- First posted on arXiv 20 Mar 2022.

## Builds on (most cited first, 30 of 33)

- [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)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned](https://mlsanity.com/paper/1905.09418/) (2019)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [Video Transformer Network](https://mlsanity.com/paper/2102.00719/) (2021)
- [SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning](https://mlsanity.com/paper/2012.09852/) (2020)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [Compressing BERT: Studying the Effects of Weight Pruning on Transfer Learning](https://mlsanity.com/paper/2002.08307/) (2020)
- [Distilling Task-Specific Knowledge from BERT into Simple Neural Networks](https://mlsanity.com/paper/1903.12136/) (2019)
- [Structured Pruning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.08571/) (2015)
- [Learned Token Pruning for Transformers](https://mlsanity.com/paper/2107.00910/) (2021)
- [Developing Real-time Streaming Transformer Transducer for Speech Recognition on Large-scale Dataset](https://mlsanity.com/paper/2010.11395/) (2020)
- [Length-Adaptive Transformer: Train Once with Length Drop, Use Anytime with Search](https://mlsanity.com/paper/2010.07003/) (2020)
- [Keyword Transformer: A Self-Attention Model for Keyword Spotting](https://mlsanity.com/paper/2104.00769/) (2021)
- [Differentiable Subset Pruning of Transformer Heads](https://mlsanity.com/paper/2108.04657/) (2021)
- [Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding](https://mlsanity.com/paper/1904.09482/) (2019)
- [Skip-Convolutions for Efficient Video Processing](https://mlsanity.com/paper/2104.11487/) (2021)

## Built on by (most cited first, 2 of 2)

- [DeltaLLM: Delta-Key Sparse Attention for Edge LLMs](https://mlsanity.com/paper/2507.19608/) (2025)
- [Onboard Optimization and Learning: A Survey](https://mlsanity.com/paper/2505.08793/) (2025)

## Abstract (arXiv)

Multi-head self-attention forms the core of Transformer networks. However, their quadratically growing complexity with respect to the input sequence length impedes their deployment on resource-constrained edge devices. We address this challenge by proposing a dynamic pruning method, which exploits the temporal stability of data across tokens to reduce inference cost. The threshold-based method only retains significant differences between the subsequent tokens, effectively reducing the number of multiply-accumulates, as well as the internal tensor data sizes. The approach is evaluated on the Google Speech Commands Dataset for keyword spotting, and the performance is compared against the baseline Keyword Transformer. Our experiments show that we can reduce ~80% of operations while maintaining the original 98.4% accuracy. Moreover, a reduction of ~87-94% operations can be achieved when only degrading the accuracy by 1-4%, speeding up the multi-head self-attention inference by a factor of ~7.5-16.